AI FOUNDATION

INTRODUCTION TO ARTIFICIAL INTELLIGENCE

History of Artificial Intelligence (AI)

Five domains of AI

Why AI now?

Limitation of AI

MACHINE LEARNING PRIMER

Machine Learning Primer

Machine Learning core concepts, scalable algorithms, project workflow.

Objective Functions and Regularization

Understanding the Objective Function of ML Algorithms

Metrics, Evaluation Methods and Optimizers

Popular Metrics in Detail: R2 Score, RMSE, Cross-Entropy, Precision, Recall, F1 Score, ROC-AUC, SGD, ADAM

Artificial Neural Network

ANN in detail, Forward Pass and Back Propagation

Machine Learning Vs Deep Learning

Core difference b/w ML and DL from an implementation perspective

ADVANCED PYTHON FOR DEEP LEARNING

Python Programming Primer

Installing Python, Programming Basics, Native Data types

Class, Inheritance and Magic Functions

Python Classes, Inheritance Concepts, Magic Functions

Special Functions in Python

Overview, Array, selecting data, Slicing, Iterating, Array Manipulations, Stacking, Splitting arrays, Key Functions

Decorators and Special Functions

Decorators implementation with class

Context Manager ‘with’ in Python

Context Manager Application

Exception Handling

Try and Catch block

Python Package Management

Bundling and export python packages

TensorFlow 2.0 AND KERAS FOR DEEP LEARNING

TensorFlow 2.0 Basics

TensorFlow core concepts, Tensors, core APIs

Concrete Functions, Data Types, Control Statements

Polymorphic Functions, Concrete Functions, Datatypes, Control Statements, NumPy, Pandas

Autograph eager execution

tf.function autograph implementation

Keras (TensorFlow 2.0 Built-in API) Overview

Sequential Models, configuring layers, loading data, train and test, complex models, callbacks, save and restore Neural Network weights

Building Neural Networks in Keras

Building Neural networks from scratch in Keras

MATHEMATICS FOR DEEP LEARNING

Linear Algebra

Vectors, Matrices, Linear Transformation, Eigen Vectors, Matrix Operations, Special Matrices

Calculus – Derivatives: Calculus essentials, Derivatives and Partial Derivatives, Chain Rule, Derivatives of special functions

Probability Essentials: Probability basics and notations, Conditional probability, Essential Probability theorems for Machine Learning

Special functions: Relu, Sigmoid, SoftMax, Popular Loss Functions – Cross-Entropy, Quadratic Loss Functions

DEEP LEARNING FOUNDATION

Deep Learning Network Concepts

Core concepts of Deep Learning Networks

Deep Dive into Activation Functions

Building simple Deep Learning Network

Tuning Deep Learning Network