Introduction to Deep Learning

This module will introduce you to the major concept called an artificial neural network, which plays a significant role in Deep Learning. You will go through the basic structure and function of these neural networks.
 

In order to enhance your understanding of the mechanism of Deep Learning or a neural net model, this module puts forth a TensorFlow Playground demo.

This module will walk you through Deep Learning concepts like artificial neural networks, activation functions, back propagation, and feed forward nets.
 

This module will let you comprehend the role of the basic set of layers in Deep Learning. You will go through Dense Layer, Dropout Layer, Convolution 1D, Convolution 2D, MaxPooling 1D, and LSTM in detail.
 

This module digs deeper into the activation function and elaborates on linear and non-linear methods of using activation functions.
 

This module contains hands-on sessions on the implementation of neural networks.

This module discusses CNN in-depth. You will be introduced to a convolutional neural network and convolutional operations, thoroughly understand its mechanism, and go through ReLu and Max pooling with examples.
 

This module starts by introducing you to Recurrent Networks. You will learn about feed forward networks and recurrency. You will also go through RNN and LSTM diagrammatic representation with a thorough explanation. Lastly, you will comprehend long short-term memory.
 

This module begins with introducing you to various use cases of types of chatbots. You will go through a diagrammatic explanation of the chatbot conversation framework and understand its role. Lastly, you will go through the conversational interfaces of chatbots.
 

This module contains an in-depth demo on CNN where you will learn its implementation through Python jupyter and understand CNN better with real-world examples.
 

This module introduces you to deep neural networks as a supervised learning method. You will go through an overview of the significant concepts you must be familiar with to understand deep neural networks better.

In this module, first, you will learn artificial neural networks to understand deep neural networks better. You will then focus on artificial neurons and their mechanism through diagrammatic representation.
 

This module discusses the boolean gates and helps you comprehend how they are effectively utilized to analyze the working of artificial neurons.
 

This module helps you understand the Rosenblatt neuron perceptron model and its functions. You will also go through its implementation using Python and understand the algorithm that plays the major role of its functions in detail through code examples.
 

This module will help you understand artificial neural network better with the help of the diagram of the Bias Layer. You will learn about a fully connected artificial neural network and the layers involved in it and go through the mathematical foundations for artificial neural networks.