Dive into a comprehensive 5-hour tutorial on deep learning, covering fundamental concepts and advanced techniques. Explore the differences between AI, ML, DL, and Data Science, and understand why deep learning is gaining popularity. Learn about perceptrons, forward and backward propagation, weight updates, and the chain rule of derivatives. Tackle challenges like the vanishing gradient problem and explore various activation functions, loss functions, and optimizers. Gain hands-on experience with practical implementations of Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN). Compare black box and white box models to deepen your understanding of deep learning architectures and their applications.
Overview
Syllabus
Introduction
AI vs ML vs DL vs Data Science
Why Deep Learning Is Becoming Popular?
Introduction To Perceptron
Working Of Perceptron With Weights And Bias
Forward Propogation,Backward Propogation And Weight Updateion Formula
Chain Rule Of Derivatives
Vanishing Gradient Problem
Different types Of Activation Functions
Different types Of Loss functions
Different type Of Optimizers
Practical Implementation OF ANN
Black Box Models VsWhite Box Models
Convolutional Neural Network
Practical Implementation Of CNN
Taught by
Krish Naik
