https://github.com/sharathraparthy/research-readings
A personal project where I publish my research paper notes on a weekly basis.
https://github.com/sharathraparthy/research-readings
deep-learning machine-learning mathemetics reinforcement-learning research-paper research-paper-summaries robotics simultion
Last synced: 12 months ago
JSON representation
A personal project where I publish my research paper notes on a weekly basis.
- Host: GitHub
- URL: https://github.com/sharathraparthy/research-readings
- Owner: SharathRaparthy
- Created: 2021-01-22T15:22:22.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2021-07-28T16:06:21.000Z (almost 5 years ago)
- Last Synced: 2025-04-06T03:15:30.523Z (over 1 year ago)
- Topics: deep-learning, machine-learning, mathemetics, reinforcement-learning, research-paper, research-paper-summaries, robotics, simultion
- Homepage: https://sharathraparthy.github.io/research-readings/
- Size: 12.7 KB
- Stars: 13
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# research-readings
Here I try to jot down my understanding of the research papers I read and also some concepts in Math/ML I find interesting. My plan is to update this repository on a weekly basis. I concentrate majorly on deep learning, reinforcement learning and some math concepts. We are also maintaining [another repository](https://github.com/IvLabs/ResearchPaperNotes) where we cover robotics literature. Please check that out if you are a roboticist.
## List of papers
* [Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/B1ngQXn2d)
* [Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/S1bZE-X3u)
* [Neurips month](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/BJo5UNk9u)
* [Deep Equilibrium Models ](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/HJwYkX9rd)
* [Universal Transformer](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rJIXkXqHu)
* [Stackelberg Actor-critic: A game theoretic perspective](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rJFUQA1QO)
* [Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/B1mLneEMu)
* [Attention is All You Need](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/HyDfftcWu)
* [Recurrent Independent Mechanisms](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/BkydH2cx_)
* [Convexity and Convergence in Gradient Descent](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/ByIMT8Zg_)
* [Notes on Stability of Dynamical Systems](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rkq_V2Cyd)
* [Radial Bayesian Neural Networks](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/SySL97y3D)
* [When do curricula work?](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rk-wOnG1u)
* [Curriculum Learning in Reinforcement Learning](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/Sy0IVj8Ju)
* [Learning Agile and Dynamic Motor Skills for Legged Robots](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/ByzYzEhVS)
* [Reinforcement Learning via Fenchel Rockafellar Duality](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rkZ5s2Y1P)
* [Off-Policy Actor-Critic](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/BkcB-xwvI)
* [Combining Physical Simulators and Object-Based Networks for Control](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/Sy6GPG9MB)
* [Notes on Reproducing Kernel Hilbert Spaces](https://hackmd.io/@FtbpSED3RQWclbmbmkChEA/rkTjKdRMS)