Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Stochastic Gradient Descent and Backpropagation

Alfredo Canziani via YouTube

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This lecture explains parameterized models, loss functions, gradient-based optimization, and backpropagation in neural networks. It includes a PyTorch implementation, generalized backpropagation, Jacobian examples, gradient computation for basic modules, and practical techniques.

Syllabus

– Week 2 – Lecture
– Gradient Descent Optimization Algorithm
– Advantages of SGD, Backpropagation for Traditional Neural Net
– PyTorch implementation of Neural Network and a Generalized Backprop Algorithm
– Basic Modules - LogSoftMax
– Practical Tricks for Backpropagation
– Computing gradients for NN modules and Practical tricks for Back Propagation

Taught by

Alfredo Canziani

Reviews

Start your review of Stochastic Gradient Descent and Backpropagation

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.