Deep Learning Project - 4A
Resources for the 4th Year's Deep Learning Project at Polytech Lyon
Subject :
Sujet 1 : Problème inverse - Tomography par émission
Sujet 2 : Apprentissage par renforcement - équilibrage d'un double pendule
Sujet 3 : Classification et segmentation faiblement supervisée de tissus cancéreux
Some videos for theoritical background :
You can start by looking at But what is a neural network REALLY by Algorithmic Simplicity. To go further the whole 3b1b's Neural networks playlist is a really good starting point. Once you finish that playlist you can return to Algorithmic Simplicity's channel and look for video about specific model.
The first two channels focus heavily on mathematics, so if you're seeking a perspective more aligned with computer science, consider checking out Sebastien Lague's video : How to Create a Neural Network (and Train it to Identify Doodles).
Before jumping into Pytorch and Tensorflow, you can try to build your own neural network from scratch to see if you fully understand the basics of backpropagation and neural network.