Module 1: Introduction

• ANN
• Neural Networks
• Activation Function
• Bias
• Bias in Neural Networks
• Data, Applications of Data, Models
• Loss Functions
• Learning Algorithms & Model Performance

Module 2: Python Basics

• Getting System Ready - Jupyter Notebook
• Accessing Google Colab Notebook
• Download Materials
• Python Basics - Data Types
• Python Basics - Containers in Python
• Control Statements Python if..else
• Python Control statments - While and For
• Functions & Classes in Python

Module 3: DS

• Numpy
• Pandas in Python - Pandas Series
• Pandas Data Frame
• Pandas Data frame - cleaning & Examining the data
• Plotting with Matplotlib
• Contour Plots

Module 4: MP Neuron Model

• MP Neuron Introduction
• MP neuron
• Intuition of data
• Loss & finding parameters
• Mathematical Intuition

Module 5: MP Neuron in Python

• MP Neuron - Data import
• Train Test Split
• Modify Data
• MP Neuron in Python
• MP Neuron Class
• Assignment for MP Neuron in Python
• Assignment Answer Submission - MP Neuron

Module 6: Perceptron

• Perceptron Model and its representation
• Loss function & Parameter Update
• Why Update Rule Works
• Update Rule in Programs.

Module 7: Sigmoid Neuron

• Percepron Limitations
• Sigmoid Neuron Introduction
• Sigmoid Neuron Data
• Sigmoid Intuition
• Manual fitting of data
• Gradient descent
• Program overview
• Program in Python

Module 8: Basic Probability

• Introduction to Probability and Random Variables
• Why Random Variable is important
• Random Variable - Types
• Probability Distribution Table
• Why do we require Entropy Loss

Module 9: Deep Neural Networks

• Why Deep Neural Networks
• Linear Separation of Data.

Module 10: Deep Learning Foundation

• Understanding Universal Approximation Theorem
• Confirming Universal Approximation Theorem Works
• Going deep into Neural Networks
• Challenges in Creating Deep Neural Networks from Scratch

Module 11: TensorFlow 2.X

• Deep Neural Networks - Recap
• Introducing Tensorflow
• Building a Neural Network with Tensorflow
• Build Neural Network with Tensorflow - HandsOn

Module 12: Activation Functions

• Activation Functions in Deep Learning Neural Networks - Introduction
• Various Activation Functions

Module 13: Network Architecture

Module 14: Applying the Deep Learning

• Moving from Shallow learning to Deep learning
• Keras Basics, Types of Problems
• ReLU
• Softmax & Cross Entropy
• Implementing Multi Class classification using keras
• Regression Problem

Module 15: Project Work & Documentation