Applied Analytics courses

 

CERTIFICATE IN MACHINE LEARNING

DEEP LEARNING AND NEURAL NETWORKS USING PYTHON

Duration 48 hours     |     Class room and online

 

COURSE OVERVIEW

1. INTRODUCTION TO MACHINE LEARNING

2. SUPERVISED LEARNING - DEEP LEARNING 

3. NEURAL NETWORKS

4. APPLIED MACHINE LEARNING

5.UNSUPERVISED LEARNING

6. SUPERVISED LEARNING 

7. REINFORCEENT LEARNING 

8. ADVANCED TOPICS

 

PRE_PROGRAM PREPARATION

UNIT 0 – INTRODUCTION TO MACHINE LEARNING

·         Supervised Learning setup

·         Unsupervised Learning setup

·         Reinforcement Learning setup

STATISTICS ESSENTIALS

UNIT I – SUPERVISED LEARNING

1.       Nearest Neighbour

2.       Linear Regression

3.       Logistic Regression

4.       Naive Bayes

5.       Curse of Dimensionalit

6.       Statistical Parameter Estimation

7.       Support Vector Machine

·         SVM Dual

·         Kernel Trick

·         Multi-class SVM

DEEP LEARNING & NEURAL NETWORKS

8.       Neural Networks

·         Multi-layer Perceptrons

·         Backpropagation

·         Introduction to Deep Learning

·         Convolutional Neural Networks

·         Recurrrent Neural Networks

9.       Decision Trees

10.   Ensemble Methods

·         Bagging

·         Boosting

·         Random Fores

APPLIED MACHINE LEARNING

UNIT II – APPLYTING MACHINE LEARNING

Bias/variance tradeoff

1.       Model selection and feature selection

2.       Advice on applying machine learning

3.       Evaluation Measures

UNIT III – UNSUPERVISED LEARNING

1.       Clustering. K-means

2.       EM. Mixture of Gaussians

3.       Factor analysis

4.       PCA (Principal components analysis)

5.       ICA (Independent components analysis)

UNIT IV – REINFORCEENT LEARNING

1.       MDPs. Bellman equations

2.       Value iteration and policy iteration

3.       Linear quadratic regulation (LQR). LQG

4.       Q-learning. Value function approximation

UNIT V – ADVANCED TOPICS

1.       Weakly-Supervised and Semi-Supervised Learning

2.       Learning Theory

·         VC dimensions

·         generalization error bounds

·         PAC Theory

3.       Adversarial machine learning

·         Generative Adversarial Networks (GANs)

4.       Graphical Models

 

DISCUSSION SECTIONS

·         Linear Algebra Review

·         Probability Theory Review

·         Convex Optimization Overview

 

DURATION

48 HOURS

                                  

PROGRAM FEE

INR. 25000 

Flexible Payment Options are Available

ELIGIBILITY

Bachelor's/Master's degrees in Computer Science/Engineering/Math/Statistics/Economics/Science/ 2 years programming experience.