This repository is dedicated to those who wish to grasp the fundamentals of AI. The resources compiled here are based on the recommendations of Ilya Sutskever, a leading figure in the AI research community and co-founder of OpenAI. By studying and understanding the papers listed in this repository, you will gain a comprehensive understanding of the current state of artificial intelligence, including its foundational theories, key breakthroughs, and practical applications.
Artificial Intelligence (AI) is an ever-evolving field, with continuous advancements shaping the technology landscape. To keep pace with these developments, it is crucial to study seminal papers that have significantly contributed to the growth and understanding of AI. This repository aims to provide a curated list of such papers, covering various aspects of AI including machine learning, neural networks, natural language processing, and more.
Ilya Sutskever, a renowned AI researcher, has recommended a selection of papers that are essential for anyone looking to understand the current landscape of AI. These papers not only cover fundamental concepts but also go into the latest advancements and innovations. By thoroughly studying these papers, you will build a strong foundation in AI and be well-equipped to contribute to future developments in the field.
- Start with the Basics: Begin with the foundational papers to build your understanding of core AI concepts.
- Progress to Advanced Topics: Move on to more advanced papers that explore cutting-edge research and applications.
- Engage with the Community: Join discussions, contribute to the repository, and share your insights with others.
This repository is a living document, and contributions are welcome. If you have suggestions for additional papers or resources, feel free to open an issue or submit a pull request.
Happy learning :)
| # | Title | Link |
|---|---|---|
| 1 | The Annotated Transformer | Link |
| 2 | Recurrent Neural Network Regularization | Link |
| 3 | Pointer Networks | Link |
| 4 | Order Matters: Sequence to Sequence for Sets | Link |
| 5 | GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism | Link |
| 6 | Deep Residual Learning for Image Recognition | Link |
| 7 | Multi-Scale Context Aggregation by Dilated Convolutions | Link |
| 8 | Neural Message Passing for Quantum Chemistry | Link |
| 9 | Attention Is All You Need | Link |
| 10 | Neural Machine Translation by Jointly Learning to Align and Translate | Link |
| 11 | Identity Mappings in Deep Residual Networks | Link |
| 12 | A Simple Neural Network Module for Relational Reasoning | Link |
| 13 | Variational Lossy Autoencoder | Link |
| 14 | Relational Recurrent Neural Networks | Link |
| 15 | Quantifying the Rise and Fall of Complexity in Closed Systems: The Coffee Automaton | Link |
| 16 | Neural Turing Machines | Link |
| 17 | Deep Speech 2: End-to-End Speech Recognition in English and Mandarin | Link |
| 18 | Scaling Laws for Neural Language Models | Link |
| 19 | A Tutorial Introduction to the Minimum Description Length Principle | Link |
| 20 | The First Law of Complexodynamics | Link |
| 21 | The Unreasonable Effectiveness of Recurrent Neural Networks | Link |
| 22 | Understanding LSTM Networks | Link |
| 23 | Keeping Neural Networks Simple by Minimizing the Description Length of the Weights | Link |
| 24 | ImageNet Classification with Deep Convolutional Neural Networks | Link |
| 25 | Machine Super Intelligence | Link |
| 26 | Kolmogorov Complexity and Algorithmic Randomness | Link |
| 27 | CS231n: Convolutional Neural Networks for Visual Recognition | Link |