Organizer: Board infinity 

Fundamentals of Deep Learning

Take up this beginner-friendly Deep learning free course and learn this form of machine learning that is inspired by how the human brain works. Deep Learning is one of the highly sought-after skills in tech. In this course, you will not just learn the important theories of deep learning, but also about how to drive your own neural network. Get a head start in your career by learning this high in-demand skill.

About the Program

Fundamentals of Deep Learning Syllabus

• Module-1 Introduction to Deep Learning and Application
• Module – 2 Artificial Neural Network and Components
• Module 3 Introduction to Convolutional Neural Networks
• Module-4 Deep-dive into CNN
• Module 5 Discussion on top CNN architectures

One Week Online FDP on Review on Recent Research in Civil Engineering : Click Here 

Apply Link

Introduction to Natural Language Processing

What is Natural Language Processing?

Natural language processing is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human languages, in particular how to program computers to process and analyze large amounts of natural language data.

Introduction to Deep Learning

This module also includes the basic structure of a neural network along with the layers of a neural network and other important concepts relating to deep learning and neural networks.

We will also learn about the difference between machine learning and deep learning and the use cases of each branch.

What is Deep Learning?

Deep learning is a subset of machine learning in which data goes through multiple numbers of non-linear transformations to obtain an output. ‘Deep’ refers to many steps in this case. The output of one step is the input for another step, and this is done continuously to get a final output. All of these steps are not linear.

Deep dive into Neural Network

In this module, we go over the concept of ANN, activation functions, gradient descent, backpropagation, and other related concepts.

What is ANN?

ANN stands for Artificial Neural Networks. Basically, it’s a computational model. That is based on the structures and functions of biological neural networks.

Writing your first Neural Network

In this module, we dive further into CNN along with its components and we will further discuss the difference between CNN and ANN and which is better.

We will also cover topics like filters, features, pooling, and padding among others.

Deep dive into CNN

In this module, we cover the important areas of global average pooling, receptive field, regularisation, and we will also walk through the code of CNN.

What is Receptive Field in CNN?

The receptive field in Convolutional Neural Networks (CNN) is the region of the input space that affects a particular unit of the network.

Advanced CNN Architectures and Training Techniques

In this module, we study the various types of architectures of neural networks along with some advanced techniques important in neural networks.

What are the main types of architecture?

They are as follows:

CNN Architecture

VggNet Architecture

Inception Architecture

ResNet Architecture

DenseNet Architecture

Basics of RNN and NLP using Deep Learning

In this module, we go over the different functions and topics that are relating to RNN and NLP, and how they are used in the world of deep learning.

Here we learn about concepts such as Word2Vec, RNN, LSTM and also go over the codes of these topics.

What is Word2Vec?

Word2vec is a group of related models that are used to produce word embeddings. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words.