CS583: Deep Learning

Machine learning basics. This part briefly introduces the fundamental ML problems-- regression, classification, dimensionality reduction, and clustering-- and the traditional ML models and numerical algorithms for solving the problems.
- ML basics [slides-1] [slides-2].
- Regression [slides-1] [slides-2].
- Classification.
  - Logistic regression [slides] [lecture note].
  - SVM [slides].
  - Softmax classifier [slides].
  - KNN classifier [slides].
- Regularizations [slides-1] [slides-2].
- Clustering [slides].
- Dimensionality reduction [slides-1] [slides-2] [lecture note].
- Scientific computing libraries. [slides].
Neural network basics. This part covers the multilayer perceptron, backpropagation, and deep learning libraries, with focus on Keras.
- Multilayer perceptron and backpropagation [slides] [lecture note].
- Keras [slides].
- Further reading:
Convolutional neural networks (CNNs). This part is focused on CNNs and its application to computer vision problems.
- CNN basics [slides].
- Tricks for improving test accuracy [slides].
- Feature scaling and batch normalization [slides].
- Advanced topics on CNNs [slides].
- Popular CNN architectures [slides].
- Further reading:
  - [style transfer (Section 8.1, Chollet's book)]
  - [visualize CNN (Section 5.4, Chollet's book)]
Recurrent neural networks (RNNs). This part introduces RNNs and its applications in natural language processing (NLP).
- Categorical feature processing [slides] [video (Chinese)].
- Text processing and word embedding [slides] [video (Chinese)].
- RNN basics [slides] [video (Chinese)].
- LSTM [slides] [reference] [video (Chinese)].
- Making RNNs more effective [slides] [video (Chinese)].
- Text generation [slides] [video (Chinese)].
- Machine translation [slides] [video (Chinese)].
- Attention [slides] [video (English)] [video (Chinese)] [reference].
- Self-attention [slides] [video (English)] [video (Chinese)].
- Image caption generation [slides] [reference].
Transformer Models.
- Transformer (1/2): attention without RNN [slides] [video (English)] [video (Chinese)].
- Transformer (2/2): from shallow to deep [slides] [video (English)] [video (Chinese)] [reference].
- BERT: pre-training Transformer [slides] [video (English)] [video (Chinese)] [reference].
- Vision Transformer (ViT) [slides] [video (English)] [video (Chinese)].
Autoencoders. This part introduces autoencoders for dimensionality reduction and image generation.
- Autoencoder for dimensionality reduction [slides].
- Variational Autoencoders (VAEs) for image generation [slides].
Generative Adversarial Networks (GANs).
- DC-GAN [slides].
Deep Reinforcement Learning.
- Reinforcement learning basics [slides] [lecture note] [video (Chinese)].
- Value-based learning [slides] [video (Chinese)].
- Policy-based learning [slides] [video (Chinese)].
- Actor-critic methods [slides] [video (Chinese)].
- AlphaGo and Monte Carlo tree search [slides] [video (Chinese)].
Parallel Computing.
- Basics and MapReduce [slides] [lecture note] [video (Chinese)].
- Parameter server and decentralized network [slides] [video (Chinese)].
- TensorFlow's mirrored strategy and ring all-reduce [slides] [video (Chinese)].
- Federated learning [slides] [video (Chinese)].
Adversarial Robustness. This part introduces how to attack neural networks using adversarial examples and how to defend from the attack.
- Data evasion attack and defense [slides] [lecture note].
- Data poisoning attack [slides] [video (Chinese)].
- Further reading: [Adversarial Robustness - Theory and Practice].
Meta Learning.
- Few-shot learning: basic concepts [slides] [video (English)] [video (Chinese)].
- Siamese network [slides] [video (English)] [video (Chinese)].
- Pretraining + fine tuning [slides] [video (English)] [video (Chinese)].
Neural Architecture Search (NAS).
- Basics [slides] [video (Chinese)].
- RNN + Reinforcement Learning: [slides] [video (Chinese)].
- Differentiable NAS: [slides] [video (Chinese)].

CS583: Deep Learning

Related tags

Overview

CS583: Deep Learning

Owner

Shusen Wang

Airborne magnetic data of the Osborne Mine and Lightning Creek sill complex, Australia

The Body Part Regression (BPR) model translates the anatomy in a radiologic volume into a machine-interpretable form.

Dark Finix: All in one hacking framework with almost 100 tools

Code Repository for Liquid Time-Constant Networks (LTCs)

Model-based 3D Hand Reconstruction via Self-Supervised Learning, CVPR2021

Code for the paper: "On the Bottleneck of Graph Neural Networks and Its Practical Implications"

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"

[NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Animashree Anandkumar, and Zhangyang Wang.

Official implementation of the paper DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.

SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning

NAACL2021 - COIL Contextualized Lexical Retriever

Official implementation of the paper "Topographic VAEs learn Equivariant Capsules"

Project for tracking occupancy in Tel-Aviv parking lots.

A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

2D&3D human pose estimation

PyKaldi GOP-DNN on Epa-DB