Maths for Deep Learning

Introduction to Matrix

Matrix Computation

Vector Algebra

Basics of Calculus

Basics of Probability

Numpy for Deep Learning

Using Numpy for Matrix Computation

Using Numpy for Calculus & Probability

Scalar, Vector, Matrices & Tensors

Functions & Convex Optimization

Neural Network

Introduction to Neural Network

Loss Functions

Building Blocks of Neural Network

Forward and backward propagation

Regularization

Implementing neural network from scratch

Implementing neural network with Keras

Training your first deep neural network

Convolutional Neural Network

Introduction to Convolutional Neural Network

Working with Images

CNN Building Blocks

CNN Architectures

Understanding Strides and Padding

Understanding Pooling Layers

Semantic Segmentation

Object Detection

Bounding Box

Building a CNN using TensorFlow & Keras

Computer Vision

Intro to OpenCV

Automated Optical Inspection

Object Segmentation & Detection

Object Classification

Object Localization

Face Recognition

Recurrent Neural Network’

Introduction to Recurrent Neural Networks

Comparing RNN with Hidden Markov Model

Understanding how Recurrent Neural Networks work

RNN Architectures

Forward Propagation

Backward Propagation through Time (BPTT)

Checkpoints & Early Stopping

Building a RNN using TensorFlow & Keras

Long Short-Term Memory (LSTM)

Problems in Sequence Predictions

Limitations of Multi-Layer Perceptrons & RNN

The Long Short-Term Memory Network

Backpropagation Training

Backpropagation through Time

Truncated Backpropagation through Time

Developing a LSTM with Keras

Developing a CNN LSTM

Developing Bi-Directional LSTM

Diagonise & Tune LSTM

Natural Language Processing

Intro to Statistical NLP Techniques

Natural Language Understanding

Working with Texts – Tokenization, Stemming, Lemmatization

Word Embeddings – Word2Vec

Word Embeddings – POS Tagging

Word Embeddings – Names Entity Recognition

Word Embeddings – TF-IDF

Natural Language Generation

NLP Applications

Implementing Autoencoders with Keras

Implementing Simple AutoEncoders

Dimensionality Reduction using AutoEncoders

Denoising Autoencoders

Changing Black & White Images into Color Images

Deep Generative Models

Generating Images with GANs

Implementing DCGANs

Implementing Variational Autoencoders