Evaluating Hypotheses: Motivation , Accuracy , A general approach for Deriving Confidence Intervals, Difference in Error of Two Hypotheses, Comparing learning algorithms.
Bayesian Belief Network
Bayesian Belief Network
Analytical Learning-Learning with perfect domain theories , Explanation Based Learning of search control knowledge
Combining Inductive and Analytical Learning: Motivation - Inductive Analytical approaches to learning
using prior knowledge to initialize the Hypothesis -EBNN & Tangent Prop
FOCL
Machine Learning Basics: Learning algorithms- capacity, overfitting and underfitting
challenges Motivating Deep Learning, Deep Feed forward Networks: Example: Learning XOR
Gradient-based Learning
Hidden units
Regularization for Deep Learning: Parameter Norm Penalties - Norm Penalties as Constrained optimization, Regularization and Under - Constrained problems
Dataset Augmentation - Noise Robustness
Semi supervised Learning - Multi-task Learning - Early stopping -Parameter tying and parameter sharing - sparse representations
Bagging and other Ensemble methods, dropout
Optimization for training Deep Models: How Learning Differs from Pure Optimization, challenges in Neural Network optimization - basic Algorithms, parameter initialization strategies, Algorithm with adaptive learning rates, approximate second-order methods, optimization strategies and meta-algorithms, Applications
