Learning Deep Learning Resources

Convolutional Neural Networks

CS231n CNN for Visual Recognition
cs231 CNN playlist youtube
CNN explainer cool visuals
Deep learning for computer vision Michigan

Neural Networks

Neural Networks: Zero to Hero
Coursera deep learning specialization

Gradient Explanations

Unserstanding Gradient Calculation
Forward and Backward prop

Generative models

MIT 6.S191: Deep Generative Modeling
Generative Adversarial Nets arXiv paper
GAN pytorch implementation
Generative Adversarial Networks faces tutorial pytorch
Lecture 19: Generative models I michigan
Lecture 20: Generative models II michigan
GAN : coursera specialization
DCGAN paper 2016 : UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS
Video Generation with TGAN
Inception score
Wasserstein GAN paper
Improved WGAN
SPECTRAL NORMALIZATION FOR GENERATIVE ADVERSARIAL NETWORKS
CATEGORICAL REPARAMETERIZATION WITH GUMBEL-SOFTMAX
From Gan To WGAN
Wasserstein GAN and the Kantorovich-Rubinstein Duality
Kernel density estimation via the Parzen-Rosenblatt window method
Interpreting the Latent Space of GANs for Semantic Face Editing

Activation functions

Vanishing gradients problem with sigmoid

Multimodal Deep Learning

Multimodal Deep Learning: Definition, Examples, Applications

Models

Implementing ResNet18 from scratch

Resnet Implementation torchvision

Object Detection

Yolo V7 paper implementation
Yolo V7 paper

Siamese Networks

Intro to siamese Networks
siamese triplet

Support Vector Machine

what is SVM
Understanding Hinge Loss and SVM cost function
What is a kernel in machine learning
Derivation of SVM Loss

Data proprocessing

Weight initialization techniques
Build Better Deep Learning Models with Batch and Layer Normalization
standard deviation explained
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Variance vs covariance
Understanding the backward pass through Batch Normalization Layer
BatchNorm Layer - Understanding and eliminating Internal Covariance Shift
How To Calculate the Mean and Standard Deviation — Normalizing Datasets in Pytorch

Analysing Results

Top 1-5 error

Ranking Loss

Understanding Ranking Loss, Contrastive Loss, Margin Loss, Triplet Loss, Hinge Loss and all those confusing names
Triplet Loss and Online Triplet Mining in TensorFlow

Ensemble learning

Ensemble of networks for improved accuracy in deep learning
code github
dataset

Transfer Learning

Transfer learning in pytorch

Regularization

Dropout (inverted dropout)

Optimization

Polyak Averaging
Stochastic Weight Averaging
Stochastic Weight Avg pytorch 1.6

PyTorch

PyTorch 2.0 release explained
A gentle intro to torch.autograd
Functionalization in PyTorch: Everything You Wanted To Know
Torch compile tutorial
AOT autograd : How to use and optimize
Making Deep learning go brrr from first principles
TensorRT
Optimizing Production PyTorch Models’ Performance with Graph Transformations

Pipeline Parallelism

Pipeline Parallelism
PiPPy

Transformers

Efficient Training on single GPU

Related Maths

Singular Value Decomposition as Simply as Possible

Compilers for Neural Networks

How Nvidia’s CUDA Monopoly In Machine Learning Is Breaking - OpenAI Triton And PyTorch 2.0
Introducing Triton: Open-source GPU programming for neural networks

Graph Neural Networks

Graph neural networks intro

Papers with code

Website for papers with code
Deep Learning using Linear SVMS
One-class Recommendation Systems with the Hinge Pairwise Distance Loss and Orthogonal Representations

Books

Modern Computer Visison with Pytorch (V Kishore)
Deep Learning with Pytorch (Eli Stevens)
Deep Learning (Ian Goodfellow, Bengio)