Beruflich Dokumente
Kultur Dokumente
LeNet-5
Object detection using R-CNN
The basic idea of R-CNN is to take a deep Neural Network
which was originally trained for image classification using
millions of annotated images and modify it for the purpose of
object detection. The basic idea from the first R-CNN paper is
illustrated in the Figure below (taken from the paper): (1)
Given an input image, (2) in a first step, a large number region
proposals are generated. (3) These region proposals, or
Regions-of-Interests (ROIs), are then each independently
sent through the network which outputs a vector of e.g. 4096
floating point values for each ROI. Finally, (4) a classifier is
learned which takes the 4096 float ROI representation as
input and outputs a label and confidence to each ROI.
Supervised vs Unsupervised
Learning
• Supervised Learning
– Data: (x, y) x is data, y is label
– Goal: Learn a function to map x -
>y
– Examples: Classification,
regression, object detection,
semantic segmentation, image
captioning, etc.
Formal neuron - perceptron
5
6
How do we actually use an artificial
neuron?
• Feedforward network: The neurons in each layer feed their
output forward to the next layer until we get the final output from
the neural network.
7
Neural Network – Back propagation
Example
https://mattmazur.com/2015/03/17/a-step-by-step-
backpropagation-example/
8
Artificial Neuron Model
Implementation of AND
function
Let W1 = W2 = 1
X1 X2 X1W1 + X2W2 Y
0 0 0 0
0 1 1 0
1 0 1 0
1 1 2 1
x1 -1 -1
1
-0.5
x2
1
-1 -1
The input sum for the neuron of the 2nd layer = Y1 – Y2 + 1
Thus the neuron of the 2nd layer separates the data correctly