Notes

CNN

RNN

Auto Encoders

• Variational Autoencoders and concept of latent space

Diffusion models

Introduction

Started in 1960's Deep Learning is a subfield of Artificial Intelligence and Machine Learning that is inspired by the structure of human brain.

• In laymen terms Deep learning mimics the human brain.

Deep learning algorithms attempt to draw similar conclusions as humans would by continually analyzing data with a given logical structure called Neural Network.

• Neural Network is inspired by the structure of human brain.
• In neural network we have an input layer, an output layer and a set of hidden layer(s).
• Examples of some Deep learning models are ANN, CNN, RNN, GAN etc.

This is also be said to be a part of a broader family of machine learning methods based on artificial neural network with representation learning.

Deep Learning Algorithms uses multiple layers to progressively extract higher-level features from the raw input.

• For example, in image processing, lower layers may identify edges, while higher layer may identify the concepts relevant to a human such as digits or letters or faces.

Why DL

Applicability: Can be applied to a wide domain of problems.

Performance: state of the art