(转) AI突破性论文及代码实现汇总

简介: 本文转自:https://zhuanlan.zhihu.com/p/25191377 AI突破性论文及代码实现汇总极视角  · 2 天前What Can AI Do For You?“The business plans of the next 10,000 startups are easy to forecast: Take X and add AI.

 

本文转自:https://zhuanlan.zhihu.com/p/25191377

 

AI突破性论文及代码实现汇总

What Can AI Do For You?

The business plans of the next 10,000 startups are easy to forecast: Take X and add AI.” — Kevin Kelly

"A hundred years ago electricity transformed countless industries; 20 years ago the internet did, too. Artificial intelligence is about to do the same. To take advantage, companies need to understand what AI can do." — Andrew Ng

If you are a newcomer to the AI, the first question you may have is "What AI can do now and how it relates to my strategies?" Here are the breakthrough AI papers and CODE for any industry.

 

Deep Learning BOOKS

  • 0.0 Deep Learning

[0] Bengio, Yoshua, Ian J. Goodfellow, and Aaron Courville. "Deep learning" An MIT Press book. (2016).

  • 0.1 Deep Reinforcement Learning

[1] Richard S. Sutton and Andrew G. Barto. "Reinforcement Learning: An Introduction (2nd Edition)"

[2] Pieter Abbeel and John Schulman | Open AI / Berkeley AI Research Lab. "Deep Reinforcement Learning through Policy Optimization"

[3] Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas. "Learning to learn by gradient descent by gradient descent"

CODE Learning to Learn in TensorFlow

arXiv Learning to Learn for Global Optimization of Black Box Functions

 

Deep Learning PAPERS

  • Papers Reading Roadmap

[0] "Deep Learning Papers Reading Roadmap"

CODE Download All Papers

  • 1.1 Neural Information Processing Systems Conference - NIPS 2016

[1] Full Videos "NIPS 2016 : 57 Episodes"

[2] CODE "All Code Implementations for NIPS 2016 papers"

  • 1.2 GitXiv : arXiv + Github + Links + Discussion

[3] arXiv + CODE "Implementations of Some of the Best arXiv Papers"

  • 1.3 Wasserstein GAN

[4] arXiv "Wasserstein GAN"

[5] CODE "Code accompanying the paper "Wasserstein GAN""

  • 1.4 The Predictron

[6] arXiv "The Predictron: End-To-End Learning and Planning"

[7] CODE "A TensorFlow implementation of "The Predictron: End-To-End Learning and Planning""

  • 1.5 Meta-RL

[8] arXiv "Learning to reinforcement learn"

[9] CODE "Meta-RL""

  • 1.6 Neural Architecture Search with RL

[10] arXiv "Neural Architecture Search with Reinforcement Learning"

  • 1.7 Superior Generalizability and Interpretability

[11] arXiv "Making Neural Programming Architectures Generalize via Recursion"

  • 1.8 Seq2seq RL GANs for Dialogue Generation

[12] arXiv "Adversarial Learning for Neural Dialogue Generation"

  • 1.9 DeepMind’s PathNet: Modular Deep Learning Architecture for AGI

[13] arXiv "PathNet: Evolution Channels Gradient Descent in Super Neural Networks"

  • 1.10 Outrageously Large Neural Networks

[14] arXiv "Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer"

 

Deep Learning TUTORIALS

  • 2.0 Implementation of Reinforcement Learning Algorithms

[0] CODE "Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course."

  • 2.1 Python Data Science Handbook

[1] CODE "Jupyter Notebooks for the Python Data Science Handbook" by Jake Vanderplas.

  • 2.2 Learn How to Build State of the Art Models

[2] Video + CODE "Practical Deep Learning For Coders, Part 1" by Jeremy Howard.

  • 2.3 NIPS 2016 Tutorial: Generative Adversarial Networks

[3] arXiv "NIPS 2016 Tutorial: Generative Adversarial Networks" by Ian Goodfellow.

  • 2.4 Data Science IPython Notebooks

[4] CODE "Data Science Python Notebooks: Deep learning (TensorFlow, Theano, Caffe), Scikit-learn, Kaggle, Big Data (Spark, Hadoop MapReduce, HDFS), Pandas, NumPy, SciPy..."

 

Deep Learning TOOLS

  • 3.0 TensorFlow

TensorFlow is an Open Source Software Library for Machine Intelligence: 

[0] Mart ́ın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mane ́, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Vie ́gas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. "WhitePaper - TensorFlow: Large-scale machine learning on heterogeneous systems"

CODE Installation

CODE TensorFlow Tutorial and Examples for Beginners

CODE Models built with TensorFlow

3.1 OpenAI Gym

The OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms OpenAI Gym: A toolkit for developing and comparing reinforcement learning algorithms

[1] Greg Brockman and Vicki Cheung and Ludwig Pettersson and Jonas Schneider and John Schulman and Jie Tang and Wojciech Zaremba. "OpenAI Gym WhitePaper"

CODE Installation of the gym open-source library

CODE How to create new environments

  • 3.2 Universe

Universe: A software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.Universe (blog).

CODE Installation

CODE Universe Starter Agent

  • 3.3 DyNet: The Dynamic Neural Network Toolkit

DyNet is a neural network library designed to be efficient when run on either CPU or GPU. DyNet has been used to build state-of-the-art systems for syntactic parsing, machine translation, morphological inflection.

[2] Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin. "DyNet: The Dynamic Neural Network Toolkit"

CODE Installation

  • 3.4 Edward: A Python library for Probabilistic Modeling, Inference and Criticism

DyNet is a neural network library designed to be efficient when run on either CPU or GPU. DyNet has been used to build state-of-the-art systems for syntactic parsingmachine translationmorphological inflection.

[2] Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin. "DyNet: The Dynamic Neural Network Toolkit"

CODE Installation

  • 3.5 DeepMind Lab: A customisable 3D platform for agent-based AI research

Edward is a Python library for probabilistic modeling, inference and criticism fusing three fields: Bayesian statistics and machine learning, deep learning, and probabilistic programming. Runs on TensorFlow.

[3] Dustin Tran, Matthew D. Hoffman, Rif A. Saurous, Eugene Brevdo, Kevin Murphy, David M. Blei. "Deep Probabilistic Programming"

CODE Installation

 

Others

  • 4.0 Robotics:Deep Reinforcement Learning

[1]"Extending the OpenAI Gym for robotics"

CODE "Gym Gazebo"

  • 4.1 Image Recognition:Very Deep Convolutional Networks

[2]"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning"

CODE"Keras-InceptionV4n"

  • 4.2 Full Resolution Image Compression:Recurrent Neural Networks

[3]"Full Resolution Image Compression with Recurrent Neural Networks"

CODE"Compression"

原文链接:ceobillionaire/WHAT-AI-CAN-DO-FOR-YOU

相关文章

资料|NIPS 2016论文实现汇总

干货福利:CVPR2016代码合集

PS.极视角高校计算机视觉算法邀请赛目前正在报名中,欢迎各高校在读学生报名参加,大奖+商业项目参与机会+数据库等你来拿!!!咨询报名请加小助手(微信号:Extreme-Vision)

相关文章
|
20天前
|
人工智能 移动开发 JavaScript
如何用uniapp打包桌面客户端exe包,vue或者uni项目如何打包桌面客户端之electron开发-优雅草央千澈以开源蜻蜓AI工具为例子演示完整教程-开源代码附上
如何用uniapp打包桌面客户端exe包,vue或者uni项目如何打包桌面客户端之electron开发-优雅草央千澈以开源蜻蜓AI工具为例子演示完整教程-开源代码附上
116 18
|
2月前
|
人工智能 C++ iOS开发
ollama + qwen2.5-coder + VS Code + Continue 实现本地AI 辅助写代码
本文介绍在Apple M4 MacOS环境下搭建Ollama和qwen2.5-coder模型的过程。首先通过官网或Brew安装Ollama,然后下载qwen2.5-coder模型,可通过终端命令`ollama run qwen2.5-coder`启动模型进行测试。最后,在VS Code中安装Continue插件,并配置qwen2.5-coder模型用于代码开发辅助。
5494 6
|
17天前
|
人工智能 开发框架 安全
Smolagents:三行代码就能开发 AI 智能体,Hugging Face 开源轻量级 Agent 构建库
Smolagents 是 Hugging Face 推出的轻量级开源库,旨在简化智能代理的构建过程,支持多种大语言模型集成和代码执行代理功能。
246 69
Smolagents:三行代码就能开发 AI 智能体,Hugging Face 开源轻量级 Agent 构建库
|
4天前
|
机器学习/深度学习 人工智能 自然语言处理
三行代码实现实时语音转文本,支持自动断句和语音唤醒,用 RealtimeSTT 轻松创建高效语音 AI 助手
RealtimeSTT 是一款开源的实时语音转文本库,支持低延迟应用,具备语音活动检测、唤醒词激活等功能,适用于语音助手、实时字幕等场景。
58 18
三行代码实现实时语音转文本,支持自动断句和语音唤醒,用 RealtimeSTT 轻松创建高效语音 AI 助手
|
8天前
|
机器学习/深度学习 人工智能 自然语言处理
Agent Laboratory:AI自动撰写论文,AMD开源自动完成科研全流程的多智能体框架
Agent Laboratory 是由 AMD 和约翰·霍普金斯大学联合推出的自主科研框架,基于大型语言模型,能够加速科学发现、降低成本并提高研究质量。
109 23
Agent Laboratory:AI自动撰写论文,AMD开源自动完成科研全流程的多智能体框架
|
15天前
|
人工智能 安全 API
OpenHands:能自主检索外部知识的 AI 编程工具,自动执行命令、网页浏览和生成代码等操作
OpenHands 是一款基于 AI 的编程工具,支持多智能体协作,能够自动生成代码、执行命令、浏览网页等,显著提升开发效率。
117 26
OpenHands:能自主检索外部知识的 AI 编程工具,自动执行命令、网页浏览和生成代码等操作
|
22天前
|
人工智能 前端开发 Unix
使用tree命令把自己的代码归类文件目录的方法-优雅草央千澈以优雅草AI智能功能为例给大家展示tree命令实际用法
使用tree命令把自己的代码归类文件目录的方法-优雅草央千澈以优雅草AI智能功能为例给大家展示tree命令实际用法
使用tree命令把自己的代码归类文件目录的方法-优雅草央千澈以优雅草AI智能功能为例给大家展示tree命令实际用法
|
7天前
|
人工智能
Scaling Laws终结,量化无用,AI大佬都在审视这篇论文
《Scaling Laws for Precision》论文提出“精度感知”的扩展理论,将精度纳入模型发展的核心考量,弥补了传统AI模型发展理论忽视精度的不足。研究发现低精度训练会降低模型的有效参数计数,影响性能,并预测了低精度训练和后训练量化带来的损失。作者通过大量实验验证了理论的可靠性和有效性,为计算资源有限情况下如何平衡模型规模和精度提供了新思路。然而,该研究也引发了关于精度与性能权衡复杂性的争议。
48 27
|
4天前
|
人工智能 JavaScript 前端开发
一段 JavaScript 代码,集成网站AI语音助手
根据本教程,只需通过白屏化的界面操作,即可快速构建一个专属的AI智能体。
|
1月前
|
人工智能 数据挖掘
AI长脑子了?LLM惊现人类脑叶结构并有数学代码分区,MIT大牛新作震惊学界!
麻省理工学院的一项新研究揭示了大型语言模型(LLM)内部概念空间的几何结构,与人脑类似。研究通过分析稀疏自编码器生成的高维向量,发现了概念空间在原子、大脑和星系三个层次上的独特结构,为理解LLM的内部机制提供了新视角。论文地址:https://arxiv.org/abs/2410.19750
76 12

热门文章

最新文章