The_Math_of_Intelligence
This is the Syllabus for Siraj Raval's new course "The Math of Intelligence"
Each week has a short video (released on Friday) and an associated longer video (released on Wednesday). So each weeks short video is in bold and the longer video is underneath.
Week 1 - First order optimization - derivative, partial derivative, convexity
SVM Classification with gradient descent
Week 2 - Second order optimization - Jacobian, hessian, laplacian
Newtons method for logistic regression
Week 3 - Vectors - Vector spaces, vector norms, matrices
K Means Clustering Algorithm
Week 4 - Matrix operations - Dot product, matrix inverse, projections
Convolutional Neural Network
Week 5 - Dimensionality Reduction - matrix decomposition, eigenvectors, eigenvalues
Recurrent Neural Network
Week 6 - Probability Theory - Bayes Theorem, Naive Bayes, Laplace Smoothing
Random Forests
Week 7 - Hyperparameter Optimization - Bayesian vs Frequentist, Distributions, Bayesian Optimization
Gaussian Mixture Models
Week 8 - Stochastic Models - Generative Networks, Latent Dirichlet Allocation, Topic Modeling
LSTM Networks
Week 9 - Reinforcement - Markov chains, Monte Carlo, Markov Decision Processes
Game Bot