Date: 6th May to 10th May 2022 Venue: Department of MCA

An online FDP session was hosted from 6^th May 2022 to 10^th May 2022 on the topic TENSORFLOW. The Guest Speaker for the session was Mr. Koustubh Prem, Associate Data Scientist, Great Learning.

Profile of the Expert:

Mr. Koustubh Prem is currently working as Associate Data Scientist at Great Learning, Bengaluru.

He is assisting as a subject matter expert at Skyfi Education Labs. He has developed a curriculum on various topics for technical and training programs. He has delivered training programs for students across the world. He is passionate to attain an engaging work position in the field of education. He is very much fascinated to help and create content that inspires people to bring the best out of themselves.

He worked as a Professional Freelancer for the conduction of Faculty Development Programs in Colleges and Training programs on Machine Learning. He is having experience in developing Data Science Projects.

He is having good experience in developing a model-based design for Quadcopter and hybrid vehicles with battery systems. He is having proficiency in Computer Vision and Machine Learning using Python and tensorFlw training programs.

Objective:

 The objective of this session is to get to learn and understand Machine Learning and Deep Learning neural networks with TensorFlow.

Content:

The session highlighted the following topics.

TensorFlow:

TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.

Tools:

 
Scikit-Learn (open-source tool designed for Data Science and Machine Learning) Programming Language : Python

Frame work : TensorFlow

IDE : Jupiter, Google Collab (web IDE)

Python Libraries for data manipulation and visualization

Machine Learning and Deep Learning Concepts:

Types of Learning: Supervised, unsupervised, semi-supervised learning and reinforcement learning types with case studies

Reinforcement Learning : Game AI, Skill Acquisition, Learning Task, Robot Navigation.

Neural Networks : A neural network is a series of algorithms that attempts to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates. In this sense, neural networks refer to systems of neurons, either organic or artificial in nature.

Activation Function : Activation function is one of the building blocks on Neural Network. Layers in Neural Network : Input Layer, Hidden Layers, Output Layer.

If the hidden layer is greater than 3, then it is called as deep neural network.

Implementation: The implementation of the deep learning model in TensorFlow using Python code was demonstrated during the session.

The life cycle model of deep learning and model building methods, advanced model features, and the procedure to improve the model performance with performance assessment methods are elaborated with case studies.