読んどきたい論文・サイトめも
はじめに
Twitterで流れてきてRTしてもすぐに流れてしまう……
それは悲しいのでこのページにどんどん追記していきます。
強化学習
A Succinct Summary of Reinforcement Learning
This document is a concise summary of many key results in single-agent reinforcement learning (RL). The intended audience are those who already have some familiarity with RL and are looking to review, reference and/or remind themselves of important ideas in the field.
ai.papers.barA survey on Transformers in Reinforcement Learning
NLP
ChatGPT
- Best-ChatGPT-Resources
ChatGPTのチュートリアルから沢山の応用先までまとまったサイト
enchanting-trader-463.notion.site
motion planning
3Dシーンでの生成
world model
- Neuro-Symbolic World Models for Adapting to Open World Novelty
Multimodal
- Multimodal Deep Learning
サーベイ論文
arxiv.org
Multimodal Deep Learning - New Book
— Jean de Nyandwi (@Jeande_d) 2023年1月14日
Multimodal learning(MML) is one of the hottest areas in AI research these days. MML has advanced a lot in recent times. We've seen models that generate images from texts, robotic actions from language & images, etc.https://t.co/O7kwsXIwZl pic.twitter.com/6iX1OI4Zpd
その他
The Forward-Forward Algorithm for Training Deep Neural Networks
- Keras実装解説
keras.io
New tutorial on https://t.co/m6mT8SaHBD: implementing the Forward-Forward algorithm, a new learning mechanism proposed by Geoffrey Hinton in 2022, that is more biologically plausible and only performs local weights updates. https://t.co/Wup81WaBy5
— François Chollet (@fchollet) 2023年1月10日