cs231n_deep_learning_for_computer_vision学习笔记

Lecture 4: Neural Networks and Backpropagation

Multi-layer Perceptron（多层感知机）

Backpropagation（反向传播）

Backprop Review Session（反向传播复习课）

Lecture 6: CNN Architectures

Batch Normalization

Transfer learning

AlexNet, VGG, GoogLeNet, ResNet

Lecture 7: Training Neural Networks

Activation functions

Data processing

Weight initialization

Hyperparameter tuning

Data augmentation

Lecture 8: Visualizing and Understanding

Feature visualization and inversion

Adversarial examples

DeepDream and style transfer

PyTorch Review Session

Lecture 9: Object Detection and Image Segmentation

Single-stage detectors

Two-stage detectors

Semantic/Instance/Panoptic segmentation

Lecture 10: Recurrent Neural Networks

RNN, LSTM, GRU

Language modeling

Image captioning

Sequence-to-sequence

Object Detection & RNNs Review Session

Lecture 11: Attention and Transformers

Self-Attention

Transformers

Lecture 12: Video Understanding

Video classification

3D CNNs

Two-stream networks

Multimodal video understanding

Midterm Review Session

In-Class Midterm

四、Reconstructing and Interacting with the Visual World

Lecture 13: Generative Models

Supervised vs. Unsupervised learning

Pixel RNN, Pixel CNN

Variational Autoencoders

Generative Adversarial Networks

Lecture 14: Self-supervised Learning

Pretext tasks

Contrastive learning

Multisensory supervision

Lecture 15: Low-Level Vision(Guest Lecture by Prof. Jia Deng from Princeton University)

Optical flow

Depth estimation

Stereo vision

Lecture 16: 3D Vision

3D shape representations

Shape reconstruction

Neural implicit representations

五、Human-Centered Applications and Implications

Lecture 17: Human-Centered Artificial Intelligence

AI & healthcare

Lecture 18: Fairness in Visual Recognition(Guest Lecture by Prof. Olga Russakovsky from Princeton University)

Final Project Poster Session