Basics of Deep Learning Part 7: Backpropagation explained – Gradient Descent and Partial Derivatives

Показать описание

In this series we are going to cover the basics of deep learning. And in this video we continue to talk about the backpropagation algorithm. Hereby, we are going to introduce the gradient descent algorithm and we are going to talk about what partial derivatives are.

Edit: At 1:06 I meant to say: "3 digits after the decimal point"

Links:

If you are wondering why the slides don’t disappear even though I am typing in the jupyter notebook, I used AutoHotkey for that. Here is an article that describes how to use it:

Sebastian Mantey

Рекомендации по теме

Комментарии

Why we cannot find a minimum by analytical approach here? Because Galois theorem. The degree of polynomial is 5, so we cannot express the roots in terms of coefficients.

jcoixgz

This is the best, the simplest, the awesome and too easy to grab explanation of gradient descent. Thank you so much for this great tutorial. You are such a gem.

AmmarAhmey

This is the best explanation of the Gradient Descent I've ever heard! Thank you very much for taking us through the whole process instead of just giving the final formula.

timur.kabizhanov

Edit: At 1:06 I meant to say: "3 digits after the decimal point"

SebastianMantey

Ups. In GENERAL CASE(!!!) you cannot solve equation of 5th degree and higher. This is Galois theorem.

jcoixgz

Solve[x^5+x - 1 ==0, x] - if you type this in Wolfram Alpha, it gives a real solution. 1/3 (-1 + (1/2 (25 - 3 sqrt(69)))^(1/3) + (1/2 (25 + 3 sqrt(69)))^(1/3)) Although it looks ugly, it's a solution

jcoixgz

Basics of Deep Learning Part 7: Backpropagation explained – Gradient Descent and Partial Derivatives

Basics of Deep Learning Part 1: Introduction

But what is a neural network? | Chapter 1, Deep learning

Deep Learning | What is Deep Learning? | Deep Learning Tutorial For Beginners | 2023 | Simplilearn

Andrew Ng's Secret to Mastering Machine Learning - Part 1 #shorts

Basics of Deep Learning Part 6: Backpropagation explained – Cost Function and Derivatives

Basics of Deep Learning Part 2: Feedforward Algorithm explained

Basics of Deep Learning Part 14: How to train a Neural Network

The Essential Main Ideas of Neural Networks

Deep Learning in Tamil | LSTM 1 | Deep Learning for Beginners | Part 12

Basics of Deep Learning Part 9: Backpropagation explained Step by Step

Basics of Deep Learning Part 7: Backpropagation explained – Gradient Descent and Partial Derivatives...

Deep Learning Basics: Introduction and Overview

Gradient descent, how neural networks learn | Chapter 2, Deep learning

Basics of Deep Learning Part 3: Implementing the Feedforward Algorithm in pure Python

AI vs Machine Learning

Learn TensorFlow and Deep Learning fundamentals with Python (code-first introduction) Part 1/2

What is Deep Learning? (in 5 Minutes) 🔥🔥

Basics of Deep Learning Part 8: Backpropagation explained – Chain Rule and Sigmoid Function

Basics of Deep Learning Part 4: Implementing the Feedforward Algorithm in pure Python cont'd

Basics of Deep Learning Part 15: Coding a Neural Network from Scratch in Python

Basics of Deep Learning Part 11: Backpropagation explained Step by Step cont'd

Introduction | Deep Learning Tutorial 1 (Tensorflow Tutorial, Keras & Python)

Basics of Deep Learning Part 5: Implementing the Feedforward Algorithm with NumPy

Tutorial : Mathematics of Deep Learning - Part 1