SUPERVISED LEARNING

  • Introduction to machine learning
  • Formal supervised learning setup, Linear regression, Normal equations
  • Gradient descent, Hypothesis classes, Overfitting and Regularization
  • Logistic regression, k-nearest neighbors
  • Probability reminder, Naive bayes classifier
  • Cross-validation, Bootstrapping
  • Decision trees
  • Tree ensemble, Random forest
  • support vector machine

UNSUPERVISED LEARNING

  • Intro to unsupervised learning, Liner algebra
  • Eigen decomposition, SVD (singular value decomposition)
  • Dimensionality reduction : PCA (principal component analysis)
  • Centroid based clustering : k-means
  • Centroid based clustering : k-medians, k-medoids, Hierarchical clustering
  • Density based clustering : DBSCAN, OPTICS
  • Distribution based clustering : GMM
  • Unsupervised learning summary and review

CONVOLUTIONAL NEURAL NETWORK

  • Intro to CNNs, Convolution, Correlation, Filtering
  • CNN Architectures
  • Detection and Segmentation
  • Visualizing and Understanding
  • Generative Adversarial Networks (GANs)
  • Advanced CNNs for computer vision

DEEP LEARNING BASICS

  • intro, history, capabilities, the perceptron
  • Neural network learning : Backpropagation
  • Practical network training
  • Autoencoders, Batch normalization
  • Why does it work? Overfitting and Generalization

ADDITIONAL METHODS, APPLICATIONS

  • Intro to statistical learning, PAC learning
  • No free lunch theorem, VC-dimension
  • the fundamental theorem of PAC learning
  • Markov model, Hidden markov model (HMM)
  • HMM algorithms

ADVANCED DEEP ARCHITECTURES

  • Recurrent Neural Network (RNNs)
  • Advanced RNN : LSTM, GRU
  • Deep reinforcement learning
  • Deep learning requires rethinking generalization (google)
  • Deep Super-resolution and image enhancement