Hello World! I'm Dipam.

A technology enthusiast, currently working as a machine learning engineer.

About me

I work at AIcrowd on many aspects of hosting research oriented competitions, especially focussed on reinforcement learning. Previously, I was at Intel, where I worked on fault detection of industrial parts. I'm optimistic about the future of AI, and strongly want to contribute to its research. Particularly, my interest lies around generalization in reinforcement learning. My undergraduate and masters studies are in Electronics and Communication Engineering, at NIT Rourkela, India. I also worked on developing an autonomous underwater vehicle from scratch, as part of Team Tiburon.

I'm a technology and science nerd. I also love to travel, go trekking, or diving.

🏕 🤖 🤿

Selected Posts

Thoughts on the ARC Benchmark

published on 2022-02-07 included in Machine Learning

Notes on the ARC benchmark, my experience at the competition, and how it can become a long-term benchmark in AI - Twitter Thread The ARC Benchmark Around the end of 2019, François Chollet released the Abstraction and Reasoning Corpus (ARC) benchmark, along with the paper On the Measure of Intelligence. And in the paper, he made a powerful claim: that deep learning cannot solve the ARC benchmark. On the surface, the tasks in the benchmark are simple.

Publications

Jennifer J Sun, Andrew Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Zachary Partridge, Alice Robie, Catherine E Schretter, Chao Sun, Keith Sheppard, Param Uttarwar, Pietro Perona, Yisong Yue, Kristin Branson, Ann Kennedy
The MABe22 Benchmarks for Representation Learning of Multi-Agent Behavior in: arXiv preprint:2207.10553 (2022)

Shengyi Huang, Rousslan Fernand Julien Dossa, Chang Ye, Jeff Braga, Dipam Chakraborty, Kinal Mehta, João G.M. Araújo
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms in: JMLR:v23 (2022)

Jennifer J Sun, Tomomi Karigo, Dipam Chakraborty, Sharada P Mohanty, Benjamin Wild, Quan Sun, Chen Chen, David J Anderson, Pietro Perona, Yisong Yue, Ann Kennedy
The multi-agent behavior dataset: Mouse dyadic social interactions in: NeurIPS Datasets and Benchmarks Track (2021)

Sharada Mohanty, Jyotish Poonganam, Adrien Gaidon, Andrey Kolobov, Blake Wulfe, Dipam Chakraborty, Graz̆vydas S̆emetulskis, João Schapke, Jonas Kubilius, Jurgis Paükonis, Linas Klimas, Matthew Hausknecht, Patrick MacAlpine, Quang Nhat Tran, Thomas Tumiel, Xiaocheng Tang, Xinwei Chen, Christopher Hesse, Jacob Hilton, William Hebgen Guss, Sahika Genc, John Schulman, Karl Cobbe
Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark in: PMLR:v133 (2021)

Bakshree Mishra, Dipam Chakraborty, Srajudheen Makkadayil, Saurabh D Patil, Bhaskar Nallani
Hardware Acceleration of Computer Vision and Deep Learning Algorithms on the Edge using OpenCL in: EAI Endorsed Transactions on Cloud Systems (2019)