type
status
date
slug
summary
tags
category
icon
password
标签
Task 1 CS231n
至于为什么eecs498半途而废选择了cs231n？
cs231n整个的学习周期比较短，而且2025 Spring的课程新加了一些前沿内容，可以快速地过一遍当前常用网络的实现原理，然后猛攻Transformer。
Assignment 1
KNN
Softmax
Two-Layer Neural Network
Image Features
Fully-Connected Neural Network
Assignment 2
Batch Normalization
Dropout
CNN
PyTorch on CIFAR-10
Image Captioning with Vanilla RNNs
Assignment 3
Image Captioning with Transformers
Self-Supervised Learning
DDPM
CLIP and DINO
Task 2 CS224r
Deep Reinforcement Learning ，也是快速过一遍然后猛攻PPO
Task MIT6.S184
Flow Matching & Diffusion Model
- Author:烬
- URL:https://myyzgg.top/article/2f4c1181-e738-80e2-8c2b-c06bd8adf460
- Copyright:All articles in this blog, except for special statements, adopt BY-NC-SA agreement. Please indicate the source!
