AI Coursework

Self designed coursework to ponder upon the every single details behind machine learning algorithms and mathematical significance.

Some of the international level courses have been taken into consideration along with practical experiment.

Courses

• STATS 202: Data Mining and Analysis

  • Course logistics
  • Supervised and unsupervised learning
  • Classification, Principal components analysis
  • Clustering
  • Linear regression
  • Classification: logistic regression
  • Classification: LDA, QDA
  • Classification examples
  • Cross validation
  • The Bootstrap
  • Model selection
  • Shrinkage
  • Dimensionality reduction
  • Splines
  • Smoothing splines, GAMS, Local regression
  • GAMs, Document analysis
  • Decision trees
  • Classification trees, Bagging, Random forests
  • Boosting, Support vector classifiers
  • Support vector machines

• CS228: Probabilistic Graphical Models: Principles and Techniques

  • Introduction, Probability Theory, Bayesian Networks
  • Undirected models
  • Learning Bayes Nets
  • Exact Inference; Message Passing
  • Sampling
  • MAP Inference; Structured prediction
  • Parameter Learning
  • Bayesian Learning; Structure Learning
  • Exponential families; variational inference

• CS221: Artificial Intelligence: Principles and Techniques

  • Linear classification Loss minimization Stochastic gradient descent
  • Features and non-linearity Neural networks, nearest neighbors
  • Generalization Unsupervised learning, K-means
  • Backpropagation and SciKit Learn
  • Tree search Dynamic programming, uniform cost search
  • A*, consistent heuristics Relaxation
  • Policy evaluation, policy improvement Policy iteration, value iteration
  • Reinforcement learning Monte Carlo, SARSA, Q-learning Exploration/exploitation, function approximation
  • Minimax, expectimax Evaluation functions Alpha-beta pruning
  • TD learning Game theory
  • AlphaZero
  • Factor graphs Backtracking search Dynamic ordering, arc consistency
  • Beam search, local search Conditional independence, variable elimination
  • CSPs
  • Bayesian inference Marginal independence Hidden Markov models
  • Forward-backward Gibbs sampling Particle filtering
  • Bayesian networks
  • Learning Bayesian networks Laplace smoothing Expectation Maximization
  • Syntax versus semantics Propositional logic Horn clauses
  • First-order logic Resolution
  • Deep learning autoencoders, CNNs, RNNs
  • semantic parsing (advanced) Higher-order logics Markov logic Semantic parsing
  • Tressider Union's Oak Lounge

• CS234: Reinforcement Learning

  • Introduction to Reinforcement Learning

  • How to act given know how the world works

    1. Tabular setting
    2. Markov processes
    3. Policy search
    4. Policy iteration
    5. Value iteration

  • Learning to evaluate a policy when don't know how the world works

  • Model-free learning to make good decisions

    1. Q-learning
    2. SARSA

  • Scaling up: RL with function approximation

  • RL with function approximation.

  • Imitation learning in large spaces

  • Policy search

  • Exploration/Exploitation

  • Meta-Learning

  • Batch Reinforcement Learning

  • Monte Carlo Tree Search

• CS229: Machine Learning

  • Introduction and Basic Concepts
  • Supervised Learning Setup
  • Linear Regression
  • Weighted Least Squares
  • Logistic Regression
  • Netwon's Method
  • Perceptron
  • Exponential Family
  • Generalized Linear Models
  • Gaussian Discriminant Analysis
  • Naive Bayes. Laplace Smoothing. Kernel Methods.
  • SVM. Kernels
  • Neural Network
  • Bias/ Variance. Regularization. Feature/ Model selection
  • Practical Advice for ML projects
  • K-means. Mixture of Gaussians. Expectation Maximization
  • GMM(EM). Factor Analysis
  • Principal Component Analysis. Independent Component Analysis
  • MDPs. Bellman Equations. Value iteration and policy iteration
  • LQR. LQG. Monte Carlo Tree Search
  • Q-Learning. Value function approximation
  • Policy Search. REINFORCE. POMDPs
  • Adversarial Machine Learning

• CS109: Introduction to Probability for Computer Scientists

  • Counting
  • Permutations and Combinations
  • Axioms of Probability
  • Conditional Probability, Bayes Theorem
  • Independence
  • Random Variables, Expectation
  • Variance, Bernoulli and Binomial
  • Discrete Distributions
  • Continuous Random Variables
  • Normal Distributions
  • Joint Distribution Functions
  • Independent Random Variables
  • Conditional Distributions
  • Beta Distributions
  • Variance From Events
  • Covariance and Samples
  • Correlation
  • Conditional Expectation
  • Central Theorems
  • Parameters and Learning
  • Maximizing Likelihood
  • Maximum A Posteriori
  • Naive Bayes
  • Logistic Regression
  • Deep Learning
  • Applied Machine Learning

• CS231N: Convolutional Neural Networks for Visual Recognition

  • Image Classification: Data-driven Approach, k-Nearest Neighbor, train/val/test splits
  • Linear classification: Support Vector Machine, Softmax
  • Optimization: Stochastic Gradient Descent
  • Backpropagation, Intuitions
  • Setting up the Architecture
  • Setting up the Data and the Loss
  • Learning and Evaluation
  • Minimal Neural Network Case Study
  • Convolutional Neural Networks: Architectures, Convolution / Pooling Layers
  • Understanding and Visualizing Convolutional Neural Networks
  • Transfer Learning and Fine-tuning Convolutional Neural Networks

• CS224N: Natural Language Processing with Deep Learning

  • Introduction and Word Vectors - Gensim word vectors example
  • Word Vectors 2 and Word Senses
  • Word Window Classification, Neural Networks, and Matrix Calculus
  • Backpropagation and Computation Graphs
  • Linguistic Structure: Dependency Parsing
  • The probability of a sentence? Recurrent Neural Networks and Language Models
  • Vanishing Gradients and Fancy RNNs
  • Machine Translation, Seq2Seq and Attention
  • ConvNets for NLP
  • Information from parts of words: Subword Models
  • Modeling contexts of use: Contextual Representations and Pretraining
  • Transformers and Self-Attention For Generative Models
  • Natural Language Generation
  • Reference in Language and Coreference Resolution
  • Multitask Learning: A general model for NLP?
  • Constituency Parsing and Tree Recursive Neural Networks
  • Safety, Bias, and Fairness
  • Future of NLP + Deep Learning

• CS238: Decision Making under Uncertainty (AA 228)

  • Probabilistic Representation
  • Probabilistic Inference
  • Parameter and Structure Learning
  • Decision Theory and Games
  • Markov Decision Processes
  • Approximate Dynamic Programming
  • Exploration and Exploitation
  • Model based Reinforcement Learning
  • State Uncertainty
  • Exact POMDP Methods
  • Hierarchical Planning
  • Deep Reinforcement Learning

• CS246: Mining Massive Data Sets

  • Introduction; MapReduce and Spark
  • Frequent Itemsets Mining
  • Recitation: Spark tutorial
  • Locality-Sensitive Hashing I
  • Recitation: Probability and Proof Techniques
  • Locality-Sensitive Hashing II
  • Recitation: Linear Algebra
  • Clustering
  • Dimensionality Reduction
  • Recommender Systems I
  • Recommender Systems II
  • PageRank
  • Link Spam and Introduction to Social Networks
  • Community Detection in Graphs
  • Algorithms on Large Graphs
  • Large-Scale Machine Learning I
  • Large-Scale Machine Learning II
  • Mining Data Streams I
  • Mining Data Streams II
  • Computational Advertising
  • Learning through Experimentation
  • Optimizing Submodular Functions

• Famous libraries for Machine Learning

  • Pandas
  • Numpy
  • Matplotlib
  • Scikit-learn
  • TensorFlow
  • Keras

• Data Processing using Spark

  • Brief into about data processing and data processing frameworks:
    1. Apache Hadoop
    2. Apache Storm
    3. Apache Samza
    4. Apache Spark
  • Performance Comparison of Apache Hadoop vs Apache Spark
  • Introduction to Apache Spark
  • Spark Features
  • Spark with Hadoop
  • Spark Components