Výsledky vyhledávání - "Chakraborty, Shuvam"

Report

Collaboration with Cellular Networks for RFI Cancellation at Radio Telescope

Autor: Chakraborty, Shuvam, Hellbourg, Gregory, Careem, Maqsood, Saha, Dola, Dutta, Aveek

The growing need for electromagnetic spectrum to support the next generation (xG) communication networks increasingly generate unwanted radio frequency interference (RFI) in protected bands for radio astronomy. RFI is commonly mitigated at the Radio

Externí odkaz: http://arxiv.org/abs/2210.17083

Zobrazit plný text záznamu

Report

IQ-Learn: Inverse soft-Q Learning for Imitation

Autor: Garg, Divyansh, Chakraborty, Shuvam, Cundy, Chris, Song, Jiaming, Geist, Matthieu, Ermon, Stefano

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount of expert

Externí odkaz: http://arxiv.org/abs/2106.12142

Zobrazit plný text záznamu

Report

Efficient Conditional Pre-training for Transfer Learning

Autor: Chakraborty, Shuvam, Uzkent, Burak, Ayush, Kumar, Tanmay, Kumar, Sheehan, Evan, Ermon, Stefano

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and improves conv

Externí odkaz: http://arxiv.org/abs/2011.10231

Zobrazit plný text záznamu

Report

Belief Propagation Neural Networks

Autor: Kuck, Jonathan, Chakraborty, Shuvam, Tang, Hao, Luo, Rachel, Song, Jiaming, Sabharwal, Ashish, Ermon, Stefano

Learned neural solvers have successfully been used to solve combinatorial optimization and decision problems. More general counting variants of these problems, however, are still largely solved with hand-crafted solvers. To bridge this gap, we introd

Externí odkaz: http://arxiv.org/abs/2007.00295

Zobrazit plný text záznamu

Report

Learning from Peers at the Wireless Edge

Autor: Chakraborty, Shuvam, Mohammed, Hesham, Saha, Dola

The last mile connection is dominated by wireless links where heterogeneous nodes share the limited and already crowded electromagnetic spectrum. Current contention based decentralized wireless access system is reactive in nature to mitigate the inte

Externí odkaz: http://arxiv.org/abs/2001.11567

Zobrazit plný text záznamu