Artificial Intelligence

Learn how the following really work

• Supervised Learning - Regression Analysis, Classification using Bayesian principles, Perceptron Learning, Neural networks/multi-layer perceptrons (MLP), Features and discriminant analysis, Support Vector Machines & Kernel methods
• Unsupervised Learning - Principal Components Analysis (PCA), K-Means clustering, Spectral clustering
• Loss functions and generalization
• Probability Theory
• Elements of Computational Learning Theory
• Bayesian inference
• Bayesian Belief Networks and Graphical models
• Gaussian Processes
• Bagging, Boosting, Random Forest
• Regression & Model-fitting Techniques - Linear regression, Polynomial Fitting, Kernel Based Networks
• Optimisation
• Linear Algebra
• Deep Learning - Deep Neural Networks (CNN, RNN)
• Deep Learning Technologies
• Deep Belief Networks- RBMs
• Learning Algorithms - Initialisation, SGD, Momentum, etc.
• Agent Interactions - Models of cooperation, Models of competitive behaviour (game theory and mechanism design), Computational markets (auctions)
• Agent design and implementation - Structuring agent models in code, Deploying agents within a simulated environment, Practical reasoning strategies for computational markets
• Classical Reinforcement - TD learning, Q learning, State Space Models
• On-line Learning - Regret minimisation, Stochastic vs. adversarial, Full information, semi-bandit, and bandit feedback
• Monte Carlo Tree Search (MCTS)
• Search - depth-first and breadth-first, iterative deepening, evolutionary algorithms, hill-climbing and gradient descent, beam search and best-first, branch and bound, dynamic programming, A*.
• Representing Knowledge - Production rules, monotonic and non-monotonic logics, semantic nets, frames and scripts, description logics
• Reasoning & Control - Data-driven and goal-driven reasoning, AND/OR graphs, truth-maintenance systems, abduction and uncertainty.
• Image formation - Sampling theorem, Fourier transform and Fourier analysis
• Image processing - Sampling and quantisation, Brightness and colour, Frequency domain processing, Histogram operations, Filters and convolution
• Boundary and line extractions
• Edge detections
• classification, recognition & clustering
• covariance, eigendecomposition and PCA
• Interest point detection
• Local features
• Segmentation
• Feature extraction
• 2-D Shape representation
• Large-scale image search & feature indexing
• Image matching
• 3D vision systems
• Vector Semantics & Embeddings - TF-IDF, Lexical and Vector Semantics, Word2Vec
• Syntactic & Semantic Parsing - Text Chunking, Word Senses & WordNet, Dependency Parsing, Syntactic parsing
• Sequence Processing with Recurrent Neural Networks - Sequence Processing for NLP Applications, Managing Context using LSTM’s and GRU’s, Recurrent Neural Networks
• Language Modelling & Speech Part Tagging - Language Modelling, Parts of Speech Tagging
• Working with Text Corpora - Regular Expressions, Text Normalization, Evaluation Metrics & Linguistic Resources
• Information Extraction - Relation Extraction, Named Entity Recognition, Temporal, Event & Location Extraction