Vision and Mission of the Department

Vision

To bring forth technically versatile, Research oriented, Industry ready engineers in the field of Artificial Intelligence and Machine Learning.

Mission

Facilitate modern infrastructure and versatile learning resources to produce self-sustainable professionals
Facilitate project based learning and skill upgradation through industry collaborations
Inculcate professional ethics, leadership qualities and practice lifelong learning

Program Specific Outcomes (PSOs):

PSO1: Graduates will have the ability to adapt, contribute and innovate ideas in the field of Artificial Intelligence and Machine Learning.
PSO2: To provide a concrete foundation and enrich their abilities to qualify for Employment, Higher studies and Research in various domains of Artificial Intelligence and Machine Learning such as Data Science, Computer Vision, Natural Language Processing with Ethical Values.
PSO3: Graduates will acquire the practical proficiency with niche technologies and open-source platforms and to become Entrepreneur in the domain Artificial Intelligence and Machine Learning.

Program Educational Objectives (PEOs):

PEO1: Attain proficiency in professional practice
PEO2: Practice technical skills to identify, analyze and solve complex problems related to Artificial Intelligence and Machine Learning.
PEO3: Emerge as an Individual or a team member with societal concerns, ethics and motivated for holistic learning.

About the Course

Deep Learning & Reinforcement Learning Deep learning is a newarea of machine learning which has gained popularity in recent past. Deep learning refers to the architectures which contain multiple hidden layers (deep networks) to learn different features with multiple levels of abstraction. Deep learning algorithms seek to exploit the unknown structure in the input distribution in order to discover good representations, often at multiple levels, with higher level learned features defined in terms of lower level features.

Deep learning algorithms can learn the right set of features, and it does this in a much better way than extracting these features using hand-coding. Instead of handcrafting a set of rules and algorithms to extract features from raw data, deep learning involves learning these features automatically during the training process.

Reinforcement learning systems are inherently end-to-end systems in which a complex task is not broken up into smaller components, but viewed through the lens of a simple reward.

Syllabus

Module 1

Introduction to Deep Learning:

Introduction, Shallow Learning, Deep Learning, Why to use Deep Learning, How Deep Learning Works,Deep Learning Challenges,. How Learning Differs from Pure Optimization, Challenges in Neural Network Optimization.

Module 2

Basics of Supervised Deep Learning:

Introduction, Convolution Neural Network, Evolution of Convolution Neural Network, Architecture of CNN, Convolution Operation.

Module 3

Training Supervised Deep Learning Networks:

Training Convolution Neural Networks, Gradient Descent-Based Optimization Techniques, Challenges in Training Deep Networks.

Supervised Deep Learning Architectures: LetNet-5,AlexNet

Module 4

Recurrent and Recursive Neural Networks :

Unfolding Computational Graphs, Recurrent Neural Network, Bidirectional RNNs, Deep Recurrent Networks, Recursive Neural Networks, The Long Short-Term Memory.Gated RNNs.

Module 5

Deep Reinforceme,nt Learning:

Introduction, Stateless Algorithms: Multi-Armed Bandits, The Basic Framework of Reinforcement Learning, case studies.

Lesson Plan

BAI701 Course Handout IPCC_PartA.pdf

Notes

Module - 1.pdf

Module-1

Important Links

E-Resources: https://cedar.buffalo.edu/%7Esrihari/

Page updated

Google Sites

Report abuse