Introduction to Artificial Intelligence

and Machine Learning

This is the ‘Introduction to Artificial Intelligence and Machine Learning’ tutorial, which
is part of the Machine Learning course offered by Simplilearn. In this tutorial, we will
learn about Machine Learning, Machine Learning benefits, and various Machine
Learning applications.

Objectives
On completion of this Machine Learning tutorial, you will learn how to:

 Define Artificial Intelligence (AI) and understand its relationship with data
 Define Machine Learning (ML) and understand its relationship with Artificial
Intelligence
 Understand Machine Learning approach and its relationship with data science
 Identify the application

Definition of Artificial Intelligence

Artificial Intelligence refers to intelligence displayed by machines that simulate
human and animal intelligence.

Data Economy
Let us quickly understand the importance of Data in brief.

 The world is witnessing the real-time flow of all types of structured and
unstructured data from social media, communication, transportation, sensors,
and devices.
 International Data Corporation (IDC) forecasts that 180 zettabytes of data will
be generated by 2025.
 This explosion of data has given rise to a new economy known as the Data
Economy.
 Data is the new oil that is precious but useful only when cleaned and
processed.
 There is a constant battle for ownership of data between enterprises to derive
benefits from it.

The Emergence of Artificial Intelligence

The data economy with its vast reservoir is enabling unprecedented innovation in
data sciences, the field which deals with extracting useful information and insights
from the available data.
Data science is going toward a new paradigm where one can teach machines to
learn from data and derive a variety of useful insights. This is known as Artificial
Intelligence.

Artificial Intelligence in Practice

Given below in this Machine Learning tutorial are a few areas where AI is used
widely.

 Self-driving cars
 Applications like Siri that understand and respond to human speech
 Google’s AlphaGo AI has defeated many Go champions such as Ke Jie
 Implementing AI in chess
 Amazon ECHO product (home control chatbot device)
 Hilton using Connie – concierge robot from IBM Watson

Data Facilitates Artificial Intelligence Products

Amazon pulls in data from its user database to recommend products to users. This
functionality helps bring in more users. More users generate even more data that
help enhance the recommendations even further.
Need to know more about Machine Learning? Click here for course preview!

What is Machine Learning?

The capability of Artificial Intelligence systems to learn by extracting patterns from
data is known as Machine Learning.

Machine Learning Benefits

Let us look at some of the benefits in this Machine Learning tutorial.

 Powerful Processing
 Better Decision Making & Prediction
 Quicker Processing
 Accurate
 Affordable Data Management
 Inexpensive
 Analyzing Complex Big Data

Features of Machine Learning

Let us look at some of the features given below in this Machine Learning tutorial.

 Machine Learning is computing-intensive and generally requires a large

amount of training data.
  It involves repetitive training to improve the learning and decision making of
algorithms.
 As more data gets added, Machine Learning training can be automated for
learning new data patterns and adapting its algorithm.

Example: Learning from new spam words or new speech (also called incremental
learning)

Artificial Intelligence and Machine Learning

Machine Learning is an approach or subset of Artificial Intelligence that is based on
the idea that machines can be given access to data along with the ability to learn
from it.

Traditional Programming vs. Machine Learning

Approach
Given below is an overview of Traditional Vs Machine Learning.

Traditional programming relies on hard-coded rules.

Machine Learning relies on learning patterns based on sample data.

As you go from rule-based systems to the deep learning ones, more complex
features and input-output relationships become learnable.
The Relationship between Data Science and Machine
Learning
Let us understand the relationship between Data Science and Machine Learning.

 Data Science and Machine Learning go hand in hand. Data Science helps
evaluate data for Machine Learning algorithms
 Data science is the use of statistical methods to find patterns in the data.
 Statistical machine learning uses the same math and techniques as data
science.
 These techniques are integrated into algorithms that learn and improve on
their own.
 Machine Learning facilitates Artificial Intelligence as it enables machines to
learn from the patterns in data.

Machine Learning Techniques

Given below are some techniques in this Machine Learning tutorial.

1. Classification
2. Categorization
3. Clustering
4. Trend analysis
5. Anomaly detection
6. Visualization
7. Decision making

Machine Learning Algorithms

Let us understand Machine Learning Algorithms in detail.

 Machine Learning can learn from labeled data (known as supervised learning)
or unlabelled data (known as unsupervised learning).
 Machine Learning algorithms involving unlabelled data, or unsupervised
learning, are more complicated than those with the labeled data or supervised
learning
 Machine Learning algorithms can be used to make decisions in subjective
areas as well.

Examples:

 Logistic Regression can be used to predict which party will win at the ballots.
 Naïve Bayes algorithm can separate valid emails from spam.

Get to know about the applications of Machine Learning. Click here for more!

Applications of Machine Learning

Some of the applications of Machine learning mentioned below.

 Image Processing
 Robotics
 Data Mining
 Video Games
 Text Analysis
 Healthcare

The table contains the details of each application in detail.

Applications Uses
 Image tagging and recognition
 Self-driving cars
Image Processing
 Optical Character Recognition (OCR)

 Human simulation
Robotics  Industrial robotics

 Anomaly detection
 Grouping and Predictions
Data Mining
 Association rules

 Some games implement reinforcement learning

Video Games
 Sentiment Analysis
 Spam Filtering
Text Analysis
 Information Extraction

 Healthcare Startups
Healthcare
Machine Learning Tutorial Overview
By the end of this Machine Learning tutorial, you will be able to:

 Master the concepts of supervised, unsupervised and reinforcement learning

concepts and modeling.
 Gain practical mastery of principles, algorithms, and applications of machine
learning through a hands-on approach which includes working on 28 projects
and one capstone project.
 Acquire thorough knowledge of the mathematical and heuristic aspects of
machine learning.
 Understand the concepts and operation of support vector machines, kernel
SVM, naive Bayes, decision tree classifier, random forest classifier, logistic
regression, K-nearest neighbors, K-means clustering and more.
 Comprehend the theoretical concepts and how they relate to the practical
aspects of machine learning.
 Be able to model a wide variety of robust machine learning algorithms
including deep learning, clustering, and recommendation systems

Target Audience
There is an increasing demand for skilled Machine Learning Engineers across all
industries, making this Machine Learning certification course well-suited for
participants at the intermediate level of experience. We recommend this Machine
Learning training course for the following professionals in particular:

 Developers aspiring to be a data scientist or machine learning engineer

 Analytics managers who are leading a team of analysts
 Business analysts who want to understand data science techniques
 Information architects who want to gain expertise in machine learning
algorithms
 Analytics professionals who want to work in machine learning or artificial
intelligence
 Graduates looking to build a career in data science and machine learning
 Experienced professionals who would like to harness machine learning in
their fields to get more insights

Let’s look into the prerequisites below in this Machine Learning Tutorial.

Prerequisites
For this Machine Learning tutorial, you should have:

 Familiarity with the fundamentals of Python programming

 The familiarity of basic high school mathematics
 An understanding of the basics of statistics
The course covers concepts of mathematics & statistics required for machine
learning, and we will provide you with a free Python course when you purchase our
Machine Learning course.
Lessons Covered
Let’s look into the lessons covered below in this Machine Learning tutorial.
Chapter
Chapter Name
No.
Introduction to Artificial
Lesson 1 Intelligence and Machine
Learning
Lesson 2 Techniques of Machine Learning
Lesson 3 Data Preprocessing
Lesson 4 Math Refresher
Lesson 5 Regression
Lesson 6 Classification
Topics
In this lesson, you will learn more about
 Artificial Intelligence
 Machine Learning
 Machine Learning algorithms
 Applications of Machine Learning
In this lesson, you will learn more about
 Supervised learning
 Unsupervised learning
 Semi-supervised and
Reinforcement learning
 Bias and variance trade-off
 Representation learning
In this lesson, you will learn more about
 Data preparation
 Feature engineering
 Feature scaling
 Datasets
 Dimensionality reduction
In this lesson, you will learn more about
 Concepts of linear algebra
 Eigenvalues, eigenvectors, and
eigendecomposition
 Introduction to Calculus
 Probability and statistics
In this lesson, you will learn more about
 Regression and its types
 Linear regression: Equations and
algorithms
In this lesson, you will learn more about
  Meaning and types of
classification
 Logistic regression
 K-nearest neighbors
 Support vector machines
 Kernel support vector machines
 Naive Bayes
 Decision tree classifier
 Random forest classifier

In this lesson, you will learn more about

Unsupervised learning:
Lesson 7  Clustering algorithms
Clustering
 K-means clustering

Key Takeaways
Let us quickly look at what you have learned so far in this Machine Learning tutorial.

 The explosion of data has given rise to a new economy known as the Data
Economy
 AI refers to the intelligence in machines that simulates human intelligence.
 The capability of AI systems to learn by extracting patterns from data is known
as Machine Learning
 Statistical machine learning uses the same math and techniques as data
science.
 Artificial intelligence and Machine learning are being increasingly used in
various functions such as image processing, text analysis, healthcare, data
mining, robotics, and video games.

Techniques of Machine Learning

This is the ‘Techniques of Machine Learning’ tutorial, which is a part of the Machine
Learning course offered by Simplilearn. We will learn various Machine Learning
techniques like Supervised Learning, Unsupervised Learning, Reinforcement
Learning, Representation Learning and a few others.

Objectives
Let us look at some of the objectives under this Techniques of Machine Learning
tutorial.

 Explain unsupervised learning with examples

 Describe semi-supervised learning and reinforcement learning
 Discuss supervised learning with examples
 Define some important models and techniques in Machine Learning
Supervised Learning: Case Study
Ever wondered how Amazon makes recommendations?

Amazon uses supervised learning algorithms to predict what items the user may like
based on the purchase history of similar classes of users. New Input Predicted
Output Algorithm Trained on Historical Data.

What is Supervised Learning?

Supervised Learning is a type of Machine Learning used to learn models from
labeled training data. It allows us to predict the output for future or unseen data.
Understanding the Algorithm of Supervised Learning
The image below explains the relationship between input and output data of
Supervised Learning.
Supervised Learning Flow
Let’s look at the steps of Supervised Learning flow:

 Data Preparation
 Training Step
 Evaluation or Test Step
 Production Deployment

Testing the Algorithm

Given below are the steps for testing the algorithm of Supervised Learning.

1. Once the algorithm is trained, test it with test data (a set of data instances that do not
appear in the training set).
2. A well-trained algorithm can predict well for new test data.
3. If the learning is poor, we have an underfit situation. The algorithm will not work well
on test data. Retraining may be needed to find a better fit.
 4. If learning on training data is too intensive, it may lead to overfitting – a situation
where the algorithm is not able to handle new testing data that it has not seen before.
The technique to keep data generic is called regularization.

Examples of Supervised Learning

Take a quick look at some examples of Supervised Learning that are given below.
Example 1: Voice Assistants like Apple Siri, Amazon Alexa, Microsoft Cortana, and
Google Assistant are trained to understand human speech and intent. Based on
human interactions, these chatbots take appropriate action.
Example 2: Gmail filters a new email into Inbox (normal) or Junk folder (Spam)
based on past information about what you consider spam.
Example 3: The predictions made by weather apps at a given time are based on
some prior knowledge and analysis of how the weather has been over a period of
time for a particular place.

Types of Supervised Learning

Given below are 2 types of Supervised Learning.

 Classification
 Regression

Classification Supervised Learning

Let us look at the classifications of Supervised learning.

 Answers “What class?”

 Applied when the output has finite and discrete values

Example: Social media sentiment analysis has three potential outcomes, positive,
negative, or neutral.
Example: Given the age and salary of consumers, predict whether they will be
interested in purchasing a house. You can perform this in your lab environment with
the dataset available in the LMS.
Regression Supervised Learning
Given below are some elements of Regression Supervised learning.
  Answers “How much?”
 Applied when the output is a continuous number
 A simple regression algorithm: y = wx + b. Example: the relationship between
environmental temperature (y) and humidity levels (x)

Example
Given the details of the area a house is located, predict the prices. You can perform
this in your lab environment with the dataset available in the LMS.
Eager to know about other Machine Learning Techniques? Click for course preview!

Unsupervised Learning: Case Study

Ever wondered how NASA discovers a new heavenly body and identifies that it is
different from a previously known astronomical object? It has no knowledge of these
new bodies but classifies them into proper categories.
NASA uses unsupervised learning to create clusters of heavenly bodies, with each
cluster containing objects of a similar nature. Unsupervised Learning is a subset of
Machine Learning used to extract inferences from datasets that consist of input data
without labeled responses.

Types of Unsupervised Learning

The 3 types of Unsupervised Learning are:

1. Clustering
2. Visualization Algorithms
3. Anomaly Detection

The most common unsupervised learning method is cluster analysis. It is used to

find data clusters so that each cluster has the most closely matched data.
Clustering
Example: An online news portal segments articles into various categories like
Business, Technology, Sports, etc.
Visualization Algorithms
Visualization algorithms are unsupervised learning algorithms that accept unlabeled
data and display this data in an intuitive 2D or 3D format. The data is separated into
somewhat clear clusters to aid understanding.
In the figure, the animals are rather well separated from vehicles. Horses are close
to deer but far from birds, and so on.

Anomaly Detection
This algorithm detects anomalies in data without any prior training. It can detect
suspicious credit card transactions and differentiate a criminal from a set of people.
What is Semi-Supervised Learning?
It is a hybrid approach (combination of Supervised and Unsupervised Learning) with
some labeled and some non-labeled data.
Example of Semi-Supervised Learning
Google Photos automatically detects the same person in multiple photos from a
vacation trip (clustering – unsupervised). One has to just name the person once
(supervised), and the name tag gets attached to that person in all the photos.

What is Reinforcement Learning?

Reinforcement Learning is a type of Machine Learning that allows the learning
system to observe the environment and learn the ideal behavior based on trying to
maximize some notion of cumulative reward.

Features of Reinforcement Learning

Some of the features of Reinforcement Learning are mentioned below.

 The learning system (agent) observes the environment, selects and takes certain
actions, and gets rewards in return (or penalties in certain cases).
 The agent learns the strategy or policy (choice of actions) that maximizes its rewards
over time.

Example of Reinforcement Learning

In a manufacturing unit, a robot uses deep reinforcement learning to identify a device
from one box and put it in a container. The robot learns this by means of a rewards-
based learning system, which incentivizes it for the right action.

Important Considerations in Machine Learning

Lets us have a quick look at some important considerations in Machine learning
below
Bias and Variance Tradeoff

 Bias refers to the error in the machine learning model due to wrong assumptions. A
high-bias model will underfit the training data.
 Variance refers to problems caused due to overfitting. This is a result of the over-
sensitivity of the model to small variations in the training data. A model with many
degrees of freedom (such as a high-degree polynomial model) is likely to have high
variance and thus overfit the training data.

Bias and Variance Dependencies

Increasing a model’s complexity will reduce its bias and increase its variance.

Conversely, reducing a model’s complexity will increase its bias and reduce its
variance. This is why it is called a tradeoff.

What is Representation Learning?

In Machine Learning, Representation refers to the way the data is presented. This
often makes a huge difference in understanding.
Example of Representation Learning
The figure shows sample data in Cartesian coordinates and polar coordinates. In this
particular case, categorization becomes easier when data is presented in a different
coordinate system. Hence, representation matters.
Linearly Separable or Not
The convergence of the learning algorithms (like perceptron) is only guaranteed if
the two classes are linearly separable and the learning rate is sufficiently small.

If the two classes can't be separated by a linear decision boundary, you can set a
maximum number of passes over the training dataset (epochs) and/or a threshold for
the number of tolerated misclassifications. The perceptron would never stop
updating the weights otherwise.
Interested in Machine Learning? Check out the course description here!

Other Machine Learning Techniques

Let us look at some of the other Machine Learning Techniques below.
Techniques Working
Probabilistic Model the probability distribution of a data set and use it to predict
Models future outcomes
Decision Trees Arrive at a hierarchical decision tree structure
Classify data based on closest data points appearing in the same
Clustering
cluster
A method to discover what items tend to occur together in a
Associated Rules
sample space
Deep Learning Based on Artificial Neural Network models

Key Takeaways
Let us run through what you have covered in this tutorial of Machine Learning
Techniques.

 Supervised Learning is a type of Machine Learning used to learn models from

labeled training data. It allows us to predict the output for future or unseen data. Two
major types of Supervised Learning are Regression and Classification.
 The ML process (for supervised learning) entails data pre-processing, training the
model, and testing the trained model and production deployment. If the training is
poor, it may lead to underfitting (model does not satisfy the test data).
 If the training is too intensive, it may lead to overfitting (the model is not able to
handle new unseen test data).
 Unsupervised Learning is a subset of Machine Learning used to extract inferences
from datasets that consist of input data without labeled responses. Some examples
of Unsupervised Learning include Clustering and Visualization algorithms.

Data Preprocessing - Machine Learning

This is the ‘Data Preprocessing’ tutorial, which is part of the Machine Learning
course offered by Simplilearn. We will learn Data Preprocessing, Feature Scaling,
and Feature Engineering in detail in this tutorial.

Objectives
Let’s look at the objectives of Data Preprocessing Tutorial.

 Recognize the importance of data preparation in Machine Learning

 Identify the meaning and aspects of feature engineering
 Standardize data features with feature scaling
 Analyze datasets and its examples
 Explain dimensionality reduction with Principal Component Analysis (PCA)

Data Preparation in Machine Learning

A quick brief of Data Preparation in Machine Learning is mentioned below.

 Machine Learning depends largely on test data.

 Data preparation is a crucial step to make it suitable for ML.
  A large amount of data is generally required for the most common forms of ML.
 Data preparation involves data selection, filtering, transformation, etc.

Data Preparation Process

The process of preparing data for Machine Learning algorithm comprises the
following:

 Data Selection
 Data Preprocessing
 Data Transformation

Data Selection
Steps involved in Data Selection involves:

 There is a vast volume, variety, and velocity of available data for a Machine Learning
problem.
 This step involves selecting only a subset of the available data.
 The selected sample must be an accurate representation of the entire population.
 Some data can be derived or simulated from the available data if required.
 Data not relevant to the problem at hand can be excluded.

Data Preprocessing
Let’s understand Data Preprocessing in detail below.
After the data has been selected, it needs to be preprocessed using the given steps:

1. Formatting the data to make it suitable for ML (structured format)

2. Cleaning the data to remove incomplete variables
3. Sampling the data further to reduce running times for algorithms and memory
requirements.

Data cleaning at this stage involves filtering it based on the following variables:
Insufficient Data
The amount of data required for ML algorithms can vary from thousands to millions,
depending upon the complexity of the problem and the chosen algorithm.
Non-Representative Data
The sample selected must be an exact representation of the entire data, as non-
representative data might train an algorithm such that it won't generalize well on new
test data.
Substandard Data
Outliers, errors, and noise can be eliminated to get a better fitment of the model.
Missing features such as age for 10% of the audience may be ignored completely, or
an average value can be assumed for the missing component.
Data Preprocessing(Contd.)
Selecting the right size of the sample is a key step in data preparation. Samples that
are too large or too small might give skewed results.
Sampling Noise
Smaller samples cause sampling noise since they get trained on non-representative
data. For example, checking voter sentiment from a very small subset of voters.
Sampling Bias
Larger samples work well as long as there is no sampling bias, that is, hen the right
data is picked. For example, sampling bias would occur when checking voter
sentiment only for the technically sound subset of voters, while ignoring others.
Example
Let us look at the Data Sample below:

Learn in detail about Data Preprocessing. Click here!

Data Transformation
The selected and preprocessed data is transformed using one or more of the
following methods:

1. Scaling: It involves selecting the right feature scaling for the selected and
preprocessed data.
2. Aggregation: This is the last step to collate a bunch of data features into a single one.

Types of Data
Lets us look at the Types of Data below.
Labeled Data or Training Data

 It is also known as marked (with values) data.

 It assists in learning and forming a predictive hypothesis for future data. It is used to
arrive at a formula to predict future behavior.
 Typically 80% of available labeled data is marked for training.

Unlabeled Data

 Data which is not marked and needs real-time unsupervised learning is

categorized as unlabelled data.

Test Data

 Data provided to test a hypothesis created via prior learning is known as test
data.
  Typically 20% of labeled data is reserved for the test.

Validation data
It is a dataset used to retest the hypothesis (in case the algorithm got overfitted to
even the test data due to multiple attempts at testing).
The illustration given below depicts how total available labeled data may be
segregated into the training dataset, test dataset, and validation dataset.

Feature Engineering
The transformation stage in the data preparation process includes an important step
known as Feature Engineering.
Definition of Feature Engineering
Feature Engineering refers to selecting and extracting the right features from the
data that are relevant to the task and model in consideration.

Feature Engineering in ML
The place of feature engineering in the machine learning workflow is shown below:

Aspects of Feature Engineering

 Most useful and relevant features are selected from the available
Feature Selection
data
Feature
Existing features are combined to develop more useful ones
Extraction
Feature Addition New features are created by gathering new data
Feature Filtering Filter out irrelevant features to make the modeling step easy

Feature Scaling
Feature scaling is an important step in the data transformation stage of the data
preparation process.
Definition of Feature Scaling
Feature Scaling is a method used in Machine Learning for standardization of
independent variables of data features.

Why Feature Scaling?

Let’s understand the importance of Feature Scaling below.

 Let’s consider a situation where input data has two features, one ranging from value
1 to 100 and the other from 1 to 10000.
 This might cause an error in machine learning algorithms, like mean squared error
method, when the optimizer tries to minimize larger errors in the second feature.
  The computed Euclidean distances between samples will be dominated by the
second feature axis in the K-nearest neighbors (KNN) algorithm.
 The solution lies in scaling all the features on a similar scale (0 to 1) or (1 to 10).

Techniques of Feature Scaling

There are 2 types of Feature Scaling.

1. Standardization
2. Normalization

Feature Scaling: Standardization

Let us understand Standardization technique below.

 Standardization is a popular feature scaling method, which gives data the property of
a standard normal distribution (also known as Gaussian distribution).
 All features are standardized on the normal distribution (a mathematical model).
 The mean of each feature is centered at zero, and the feature column has a standard
deviation of one.

Standardization: Example
To standardize the jth feature, you need to subtract the sample mean uj from every
training sample and divide it by its standard deviation σj as given below:

Here, xj is a vector consisting of the jth feature values of all training samples n.

Given below is a sample NumPy code that uses NumPy mean and standard
functions to standardize features from a sample data set X (x0, x1...) :

The ML library scikit-learn implements a class for standardization called

StandardScaler, as demonstrated here:
Feature Scaling: Normalization
In most cases, normalization refers to the rescaling of data features between 0 and
1, which is a special case of Min-Max scaling.
Normalization: Example
In the given equation, subtract the min value for each feature from each feature
instance and divide by the spread between max and min.

In effect, it measures the relative percentage of distance of each instance from the
min value for that feature.
The ML library scikit-learn has a MinMaxScaler class for normalization.

Difference between Standardization and Normalization

The following table shows the difference between standardization and normalization
for a sample dataset with values from 1 to 5:

Datasets in Machine Learning

Given below are the Datasets in Machine Learning.

 Machine Learning problems often need training or testing datasets.

 A dataset is a large repository of structured data.
 In many cases, it has input and output labels that assist in Supervised Learning.
IRIS Dataset
IRIS flower dataset is one of the popular datasets available online and widely used to
train or test various ML algorithms.

MNIST Dataset
Modified National Institute of Standards and Technology (MNIST) dataset is another
popular dataset used in ML algorithms.

 National Institute of Standards and Technology (NIST) is a measurement standards

laboratory and a non-regulatory agency of the US Department of Commerce.
 Modified NIST (MNIST) database is a collection of 70,000 handwritten digits and
corresponding digital labels
 The digital labels identify each of these digits from 0 to 9.
 It is one of the most common datasets used by ML researchers to test their
algorithms.

Growing Datasets
As the amount of data grows in the world, the size of datasets available for ML
development also grows:
Dimensionality Reduction
Let’s look at some aspects of Dimensionality Reduction below.

 Dimensionality reduction involves the transformation of data to new dimensions in a

way that facilitates discarding of some dimensions without losing any key information.
 Large-scale problems bring about several dimensions that can become very difficult
to visualize
 Some of such dimensions can be easily dropped for a better visualization.

Example: Car attributes might contain maximum speed in both units, kilometer per
hour, and miles per hour. One of these can be safely discarded in order to reduce
the dimensions and simplify the data.

Dimensionality Reduction with Principal Component

Analysis
Below mentioned are some of the Dimensionality Reduction aspects.

 Principal component analysis (PCA) is a technique for dimensionality reduction that

helps in arriving at better visualization models.
 Let’s consider the pilots who like to fly radio-controlled helicopters. Assume x1 = the
piloting skill of the pilot and x2 = passion to fly.
 RC helicopters are difficult to fly and only those students that truly enjoy flying can
become good pilots. So, the two factors x1 and x2 are correlated, and this correlation
may be represented by the piloting “karma” u1 and only a small amount of noise lies
off this axis (represented by u2 ).
 Most of the data lie along u1, making it the principal component.
 Hence, you can safely work with u1 alone and discard u2 dimension. So, the 2D
problem now becomes a 1D problem.

Keen on learning Machine Learning? Click for course description!

Principal Component Analysis (PCA)

Let’s look at some aspects of Principal Component Analysis below.

 Before the PCA algorithm is developed, you need to preprocess the data to
normalize its mean and variance.
  Steps 1 and 2 reduce the mean of the data, and steps 3 and 4 rescale each
coordinate to have unit variance. It ensures that different attributes are treated on the
same scale.
 For instance, if x1 was maxed speed in mph (taking values in high tens or low
hundreds) and x2 was the number of seats (taking values 2-4), then this
renormalization rescales the attributes to make them more comparable to each other.

Principal Component Analysis (PCA)(Contd.)

How do you find the axis of variation u on which most of the data lies?

 When you project this data to lie along the axis of the unit vector, you would like to
preserve most of it, such that its variance is maximized (which means most data is
covered).
 Intuitively, the data starts off with some amount of variance (information).
 The figure shows this normalized data.

 Let’s project data onto different u axes as shown in the charts given on the left.
 Dots represent the projection of data points on this line.
 In figure A, projected data has a large amount of variance, and the points are far from
zero.
 In figure B, projected data has a low amount of variance, and the points are closer to
zero.
 Hence, figure A is a better choice to project the data.
 The length of projection of x on a unit vector u is given by xTu. This also represent
the distance of the projection of x from the origin.
 Hence, to maximize the variance of the projections, you can choose a unit length u:

 You get the principal Eigenvector* of

 It is also known as the covariance matrix of the data (assuming that it has zero
mean).
 Generally, if you need to project data onto the k-dimensional subspace (k < n), you
choose u1, u2...uk to be the top k Eigenvectors of ∑.
 All the ui now form a new orthogonal basis for the data.
  Then, to represent x(i) in this new basis, you need to compute the corresponding
vector:

 The vector y(i) is a lower k-dimensional approximation of x(i). This is known as the
dimensionality reduction.
 The vectors u1,u2...uk are called the first k principal components of the data.

Applications of PCA
Given below are the application of PCA.
Noise Reduction
PCA can eliminate noise or noncritical aspects of the data set to reduce complexity.
Also, during image processing or comparison, image compression can be done with
PCA, eliminating the noise such as lighting variations in face images.
Compression
It is used to map high dimensional data to lower dimensions. For example, instead of
having to deal with multiple car types (dimensions), we can cluster them into fewer
types.
Preprocess
It reduces data dimensions before running a supervised learning program and saves
on computations as well as reduces overfitting.

PCA: 3D to 2D Conversion
3D Data ----changes to----- After PCA, one finds only two dimensions being
important—Red and Green that carry most of the variance. The blue dimension has
limited variance, and hence it is eliminated.
Key Takeaways
Let us go through what you have learned so far in this Data Preprocessing tutorial.

 Data preparation allows simplification of data to make it ready for Machine Learning
and involves data selection, filtering, and transformation.
 Data must be sufficient, representative of real-world data, and of high quality.
 Feature Engineering helps in selecting the right features and extracting the most
relevant features.
 Feature scaling transforms features to bring them on a similar scale, in order to make
them comparable in ML routines.
 Dimensionality Reduction allows reducing dimensions in datasets to simplify ML
training.

TOP 5 DEEP LEARNING TRENDS

THAT WILL DOMINATE 2019
DEEP LEARNING LATEST NEWS
by Kamalika Some October 3, 2018 0 comments
Deep learning a subset of machine learning comes under the realms of artificial
intelligence (AI) and works by gathering huge datasets to make machines act like
humans. Deep learning having immense potential uses machine learning to tackle
new complex problems like speech, language and image recognition by giving
machines the power to learn how features in the data combine into increasingly
higher level, abstract forms. The deployment of neural networks has aided deep
learning to produce optimized results. Deep learning has immense adaptability, like
how Facebook uses deep learning to automatically find friends in an image and
suggests the user to tag them.

The Bright Market for Deep Learning

According to a leading source, the deep learning market is expected to exceed $18
billion by 2024, growing at a CAGR of 42%. Deep learning algorithms have a huge
potential and take messy data like video, images, audio recordings, and text to make
business-friendly predictions. Deep learning systems form a strong foundation of
modern online services, used by giants like Amazon to understand what the users
say understanding speech and the language they use through Alexa virtual assistant
or by Google to translate text when the users visit a foreign-language website.

2019 and years to come will be dominated by deep learning trends that will create a
disrupting impact in the technology and business world, here are the Top 5 Deep
Learning Trends that will dominate 2019.

1. Training Datasets Bias will Influence AI

Human bias is a significant challenge for a majority of decision-making models. The
difference and variability of artificial intelligence algorithms are based on the inputs
they are fed. Data scientists have come to a conclusion that even machine learning
solutions have their own biases that may compromise on the integrity of their data
and outputs. Artificial intelligence biases can go undetected for a number of reasons,
prominently being training data biases. Bias in training datasets impacts real-world
applications that have come up from the biases in machine learning datasets
including poorly targeted web-based marketing campaigns, racially discriminatory
facial recognition algorithms and gender recruiting biases on employment websites.

2. AI will Rise Amongst Business and Society

Gone are the times when AI was the toast of sci-fi movies, but technology has finally
caught up with imagination and adaptability. In the present times, AI has become a
reality and amazingly, business and society encounter some form of artificial
intelligence in their everyday operations.

Deep learning has dramatically improved the way we live and interact with
technology. Amazon’s deep learning offering Alexa is powered to carry out a number
of functions via voice interactions, like playing music, making online purchases and
answering factual questions. Amazon’s latest offering, AmazonGo that works on AI
allows shoppers to walk out of a shop with their shopping bags and automatically get
charged with a purchase invoice sent directly to their phone.

3. AI Reality, the Hype will Outrun Reality

Deep learning powered Robots that serve dinner, self-driving cars and drone-taxis
could be fun and hugely profitable but exists in far off future than the hype suggests.
The overhype surrounding AI and deep learning will propel venture capitalists to
redirect their capital elsewhere to the next big thing like 4d printing or quantum
computing. Entry bars for deep learning project investments will be higher and at that
point, the AI bubble will plunge. To avoid that, technology needs to help users to
recognize that AI, machine learning, and deep learning are much more than just
buzzwords and have the power to make our every day much easier. Reality says the
time is ripe to spend fewer efforts on the exploration of deep learning possibilities
and instead focus on delivering solutions to actual, real-life problems.

4. Solving The ‘Black Box’ Problem with Audit Trails

AI and its adaptability come with one of the biggest barriers to its deployment
particularly in regulated industries, is the explanation as to how AI reached a
decision and gave its predictions. 2019 will mark a new era in creating AI audit trails
explaining the nitty-gritties of how AI and deep learning reach a conclusion.

In the future times to come, AI will be explored and deployed for groundbreaking
applications like drug discovery which can have a detrimental impact on human life if
an incorrect decision is made. Thus, audit trails to AI and deep learning predictions
are extremely important.

5. AI Innovations will be Built on Cloud Adoption Capabilities

Come 2019 and beyond and business enterprises will seek to improve their
technological infrastructure and cloud hosting processes for supporting their machine
learning and AI efforts. As deep learning makes businesses innovate and improve
with their machine learning and artificial intelligence offerings, more specialized
tooling and infrastructure will be needed to be hosted on the cloud to support
customised use cases, like solutions for merging multi-modal sensory inputs for
human interaction (like think sound, touch, and vision) or solutions for merging
satellite imagery with financial data for enhanced trading capabilities.

Every company is now a data company, capable of using machine learning in the
cloud to deploy intelligent apps at scale, thanks to three machine learning
trends: data flywheels, the algorithm economy, and cloud-hosted intelligence.

That was the takeaway from the inaugural Machine Learning / Artificial Intelligence
Summit, hosted by Madrona Venture Group* last month in Seattle, where more than
100 experts, researchers, and journalists converged to discuss the future of artificial
intelligence, trends in machine learning, and how to build smarter applications.
With hosted machine learning models, companies can now quickly analyze large,
complex data, and deliver faster, more accurate insights without the high cost of
deploying and maintaining machine learning systems.

“Every successful new application built today will be an intelligent application,” Soma
Somasegar said, venture partner at Madrona Venture Group. “Intelligent building
blocks and learning services will be the brains behind apps.”

Below is an overview of the three machine learning trends leading to a new

paradigm where every app has the potential to be a smart app.

Data Flywheels

Digital data and cloud storage follow Moore’s law: the world’s data doubles every two
years, while the cost of storing that data declines at roughly the same
rate. This abundance of data enables more features, and better machine learning
models to be created.

“In the world of intelligent applications, data will be king, and the services that can
generate the highest-quality data will have an unfair advantage from their data
flywheel — more data leading to better models, leading to a better user experience,
leading to more users, leading to more data,” Somasegar says.
For instance, Tesla has collected 780 million miles of driving data, and they’re
adding another million every 10 hours.

This data is feed into Autopilot, their assisted driving program that uses ultrasonic
sensors, radar, and cameras to steer, change lanes, and avoid collisions with little
human interaction. Ultimately, this data will be the basis for their autonomous, self-
driving car theyplan to release in 2018.

Compared to Google’s self-driving program, which has amassed just over 1.5 million
miles of driving data. Tesla’s data flywheel is in full effect.

The Algorithm Economy

All the data in the world isn’t very useful if you can’t leverage it. Algorithms are how
you efficiently scale the manual management of business processes.

“Everything at scale in this world is going to be managed by algorithms and data,”

says Joseph Sirosh, CVP of Data Group and Machine Learning at Microsoft. In the
near-future, “every business is an algorithmic business.”

This creates an algorithm economy, where algorithm marketplaces function as the

global meeting place for researchers, engineers, and organizations to create, share,
and remix algorithmic intelligence at scale. As composable building blocks,
algorithms can be stacked together to manipulate data, and extract key insights.
In the algorithm economy, state-of-the-art research is turned into functional, running
code, and made available for others to use. The intelligent app stack illustrates the
abstraction layers, which form the building blocks needed to create intelligent apps.

“Algorithm marketplaces are similar to the mobile app stores that created the ‘app
economy,'” Alexander Linden, research director at Gartner said. “The essence of the
app economy is to allow all kinds of individuals to distribute and sell software globally
without the need to pitch their idea to investors or set up their own sales, marketing
and distribution channels.”
Cloud-Hosted Intelligence

For a company to discover insights about their business, using algorithmic machine
intelligence to iteratively learn from their data is the only scalable way. It’s historically
been an expensive upfront investment with no guarantee of a significant return.

“Analytics and data science today are like tailoring 40-years ago,” Sirosh said. “It
takes a long time and a tremendous amount of effort.”

For instance, an organization needs to first collect custom data, hire a team of data
scientists, continually develop the models, and optimize them to keep pace with the
rapidly changing and growing volumes of data — that’s just to get started.

With more data becoming available, and the cost to store it dropping, machine
learning is starting to move to the cloud, where a scalable web service is an API call
away. Data scientists will no longer need to manage infrastructure or implement
custom code. The systems will scale for them, generating new models on the fly, and
delivering faster, more accurate results.

“When the effort to build and deploy machine learning models becomes a lot less —
when you can ‘mass manufacture’ it — then the data to do that becomes widely
available in the cloud,” Sirosh said.

Emerging machine intelligence platforms hosting pre-trained machine learning

models-as-a-service will make it easy for companies to get started with ML, allowing
them to rapidly take their applications from prototype to production.
“As companies adopt the microservices development paradigm, the ability to plug
and play different machine learning models and services to deliver specific
functionality becomes more and more interesting,” Somasegar said.

When open source machine learning and deep learning frameworks running in the
cloud, like Scikit-Learn, NLTK, Numpy, Caffe, TensorFlow, Theano, or Torch,
companies will be able to easily leverage pre-trained, hosted models to tag images,
recommend products, and do general natural language processing tasks.

Recap of Machine Learning Trends

“Our world view is that every company today is a data company, and every
application is an intelligent application,” Somasegar said. “How can companies get
insights from huge amounts of data and learn from that? That’s something that has
to be brought up with every organization in the world.”

As the data flywheels begin to turn, the cost to acquire, store, and compute that data
will continue to drop.

This creates an algorithm economy, where the building blocks of machine

intelligence live in the cloud. These pre-trained, hosted machine learning models
make it possible for every app to tap into algorithmic intelligence at scale.

The confluence of data flywheels, the algorithm economy, and cloud-hosted

intelligence means:

 Every company can now be a data company

 Every company can now access algorithmic intelligence
 Every app can now be an intelligent app

The Future of Machine Learning and

Artificial Intelligence
By Paramita Ghosh on October 16, 2018

TwitterFacebookGoogle+LinkedIn
 Artificial Intelligence (AI) and associated
technologies will be present across many industries, within a considerable number of
software packages, and part of our daily lives by 2020. Gartner has also predicted that by
2020, AI will become one of the top five investment priorities for at least 30 percent of Chief
Information Officers. Global software vendors are after this new gold rush. Unfortunately,
though the promise of new revenue has pushed software business owners to invest in AI
technologies, the truth is that most organizations do not have skilled staff to embrace AI.

An implicit note of warning in many industry surveys on AI and its impact on industries is
that software vendors should first focus on understanding the business-customer needs and
potential business benefits from AI, before chasing the gold rush, which has been termed as
“AI Washing,” as suggested in How Enterprise Software Providers Should (and Should Not)
Exploit the AI Disruption.

The trust deficit in the “capabilities of tech-enabled solutions” that exists today will vanish in
the next 10 years, states In Ten Years: The Future of AI and ML. Over the next decade, we
will witness a radical shift from partial mistrust and skepticism to complete dependence on
AI and other advanced technologies. Most AI-powered applications are consumer facing,
which is another solid reason for mainstream users to overcome the trust barrier over time.
With more exposure and more access to technological solutions for their daily business, the
Citizen Data Science community will pave the way for a new-technology-order world.

Leveraging AI and Machine Learning as Competitive Business Drivers claims that while
technologies like the Cloud brings agility to business processes, AI and Machine Learning
have the power to influence business outcomes.

According to Gartner:

“Artificial Intelligence and Machine Learning have reached a critical tipping point and will
increasingly augment and extend virtually every technology enabled service, thing, or
application.”

The Future of AI

In the post-industrialization era, people have worked to create a machine that behaves like a
human. The thinking machine is AI’s biggest gift to humankind; the grand entry of this self-
propelled machine has suddenly changed the operative rules of business. In the recent years,
 self-driving vehicles, digital assistants, robotic factory staff, and smart cities have proven that
intelligent machines are possible. AI has transformed most industry sectors like retail,
manufacturing, finance, healthcare, and media and continues to invade new territories.

The Future of Machine Learning

Here are some predictions about Machine Learning, based on current technology trends and
ML’s systematic progression toward maturity:

 ML will be an integral part of all AI systems, large or small.

 As ML assumes increased importance in business applications, there is a strong possibility of this
technology being offered as a Cloud-based service known as Machine Learning-as-a-Service (MLaaS).
 Connected AI systems will enable ML algorithms to “continuously learn,” based on newly emerging
information on the internet.
 There will be a big rush among hardware vendors to enhance CPU power to accommodate ML data
processing. More accurately, hardware vendors will be pushed to redesign their machines to do
justice to the powers of ML.
 Machine Learning will help machines to make better sense of context and meaning of data.

The blog post, 5 Predictions for the Future of Machine Learning from IBM Big Data Hub,
offers descriptions of the above trends.

Some Predictions about Machine Learning

A seasoned user of ML techniques shares his insights into the world of ML, suggesting these
trends are imminent in the field of ML:

 Use of Multiple Technologies in ML: The emergence of IoT has benefitted Machine Learning in many
ways. The use of multiple technological strategies to achieve better learning is currently is practice in
ML; in the future more “collaborative learning” by utilizing multiple technologies is probable.
 Personalized Computing Environment: Developers will have access to API kits to design and deliver
“more intelligent application.” In a way, this effort is akin to “assisted programming.” Through these
API kits, developers will easily embed facial, speech, or vision-recognition features into their
systems.
 Quantum Computing will greatly enhance the speed of execution of ML algorithms in high-
dimensional vector processing. This will be the next conquest in the field of ML research.
 Future advancement in “unsupervised ML algorithms” will lead to higher business outcomes.
 Tuned Recommendation Engines: ML-enabled services of the future will become more accurate and
relevant. For example, the Recommendation Engines of the future will be far more relevant and
closer to an individual user’s personal preferences and tastes.

Machine Learning and Artificial Intelligence Trends in 2018 provides a quick roundup of the
most salient technology trends for 2018. Gartner’s Top 10 Technology Trends of 2017 sums
up the all-pervading digital fever as the existence of people, machines, and business
processes in a unified system.

Will Advanced AI and ML Affect Cyber security?

Going by the current research trends in AI and ML, the advancements in cyber-security has
taken ML algorithms to the next level of learning, which suggests the security-centric AI and
ML applications of the future will be marked for their speed and accuracy. The full story is
available in Machine Learning, Artificial Intelligence & the Future of Cyber Security. This
growing trend may bring Data Scientists and cyber security experts closer to achieving
common software-development goals.

Benefiting Humanity: AI and ML in Core Industry Sectors

It is hard to ignore the global impact of “AI Washing” in the current business market, and
how AI and ML may change the application-development markets of tomorrow.

AI and ML have jointly been given the same importance as the discovery of electricity at the
beginning of Industrial Revolution. These frontier technologies, just like electricity, have
ushered in a new era in the history of Information Technology.

Today, AI- and ML-powered systems are drastically changing the way business is done
across all industry sectors. These frontier technologies are gradually bringing about
transformative changes across industry sectors, a few of which are listed here:

In Healthcare

Gradually, human practitioners and machines will work in tandem to deliver improved
outcomes. Advanced machines will be expected to deliver accurate and timely diagnosis of
patient conditions, while the practitioners can focus more on patients.

In Finance
AI And Machine Learning are the New Future Technology Trends discusses how the latest
technologies like blockchain are impacting India’s capital markets. For instance, capital-
market operators can use blockchain to predict movements in the market and to detect fraud.
AI technologies not only provide opportunities for newer business models in the financial
market, but also solidify the AI technologist’s position in the business-investment ecosystem.

In Real Estate
Contactually.com, an advanced CRM system for the real estate business, has been
specifically designed to connect Washington DC-based investors and startups. The additional
power of Machine Learning algorithms transforms the static system into a live, interactive
machine, which responds, approves, and recommends.

In Database Administration
The repetitive tasks in an average DBA system provide opportunity for AI technologies to
automate processes and tasks. Today’s DBA is empowered with advanced tools, so that they
can make value-added contributions to their organizations rather than just performing rote
functions, as explored in What Do AI and Machine Learning Mean for DBAs.

In the Personal Device Market

Some business analysts at claim that AI is a game changer for the personal device market. By
2020, about 60 percent of personal-device technology vendors will depend on AI-enabled
Cloud platforms to deliver enhanced functionality and personalized services. AI technology
will deliver an “emotional user experience.”