Beruflich Dokumente
Kultur Dokumente
(Deep Learning)
Taesup Moon
Lecture 2
• Review
– Probability
(http://web.stanford.edu/class/cs224n/readings/cs229-prob.pdf)
– Linear algebra
(http://web.stanford.edu/class/cs224n/readings/cs229-linalg.pdf)
– Convex optimization
(http://web.stanford.edu/class/cs224n/readings/cs229-cvxopt.pdf)
– Information theory
• Axioms of probability
• Joint probability
– Sum rule
– Product rule
• Conditional probability
• Bayes’ rule
• Random variables
– Discrete
– Continuous
• Independence
• Conditional independence
• Covariance
• Entropy
– Measure of uncertainty
– Lower limit of data compression
• Relative entropy
– Also known as Kullback-Leibler (KL) divergence
– Often used as a distance between two distributions
à Rigorously, not a metric, though.
• Matrix, vector
• Norms
• Eigenvalues / eigenvectors
• Matrix calculus
– Gradient, Jacobian matrix
– Hessian
• Convex set
• Convex function
Jensen’s Inequality
• Convex optimization