Definition of learning systems-Goals and applications of machine learning- Types of Machine Learning- Machine Learning Process-Terminology-Weight Space-The Curse of Dimensionality- Testing Machine Learning Algorithms

Regression: Linear Regression –Parametric Models- Multivariate Regression. Classification: Bayesian Decision Theory-parametric and non-parametric methods- Multivariate Classification-Logistic Regression- K-Nearest Neighbor classifier. Decision Tree based methods for classification and Regression- Ensemble methods.

Introduction-Clustering-K-means clustering, EM algorithm, Hierarchical Clustering- Principal Component Analysis- Probabilistic PCA.

The Brain and The Neuron-Neural Networks-Perceptron-Training the perceptron -Perceptron Learning Algorithm- Multilayer Perceptron- Back Propagation -Dimensionality Reduction.

Convolutional Networks, Recurrent Neural Networks, Bidirectional RNNs, Deep Recurrent Networks, Recursive Neural Networks, Applications – Speech Recognition.