1 code implementation • 5 Feb 2024 • Mikel Bober-Irizar, Soumya Banerjee
We present the Perceptual Abstraction and Reasoning Language (PeARL) language, which allows DreamCoder to solve ARC tasks, and propose a new recognition model that allows us to significantly improve on the previous best implementation. We also propose a new encoding and augmentation scheme that allows large language models (LLMs) to solve ARC tasks, and find that the largest models can solve some ARC tasks.
no code implementations • 1 Dec 2023 • S. VenkataKeerthy, Yashas Andaluri, Sayan Dey, Soumya Banerjee, Ramakrishna Upadrasta
We show results on several standard projects and on real-world vulnerabilities.
1 code implementation • 28 Nov 2023 • Soumya Banerjee, Sarada Prasad Gochhayat, Sachin Shetty
This work investigates transmission data from fixed broadband wireless access in the mmWave band in 5G.
1 code implementation • 28 Nov 2023 • Soumya Banerjee, Sandip Roy, Sayyed Farid Ahamed, Devin Quinn, Marc Vucovich, Dhruv Nandakumar, Kevin Choi, Abdul Rahman, Edward Bowen, Sachin Shetty
In this paper, we propose an enhanced Membership Inference Attack with the Batch-wise generated Attack Dataset (MIA-BAD), a modification to the MIA approach.
no code implementations • 28 Nov 2023 • Ying Wang, Shashank Jere, Soumya Banerjee, Lingjia Liu, Sachin Shetty, Shehadi Dayekh
To address this, an unsupervised auto-encoder-based anomaly detection is presented with an AUC of 0. 987.
no code implementations • 28 Nov 2023 • Soumya Banerjee, Debarshi Kumar Sanyal, Samiran Chattopadhyay, Plaban Kumar Bhowmick, Partha Pratim Das
Digital libraries often face the challenge of processing a large volume of diverse document types.
Document Image Classification Optical Character Recognition (OCR)
no code implementations • 15 Sep 2023 • Soumya Banerjee, Vinay K. Verma, Avideep Mukherjee, Deepak Gupta, Vinay P. Namboodiri, Piyush Rai
Streaming lifelong learning is a challenging setting of lifelong learning with the goal of continuous learning in a dynamic non-stationary environment without forgetting.
no code implementations • 27 Jan 2023 • Soumya Banerjee, Vinay Kumar Verma, Vinay P. Namboodiri
Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups.
no code implementations • 20 Oct 2021 • Soumya Banerjee, Vinay Kumar Verma, Toufiq Parag, Maneesh Singh, Vinay P. Namboodiri
We propose a novel approach (CIOSL) for the class-incremental learning in an \emph{online streaming setting} to address these challenges.
no code implementations • 29 Mar 2021 • Rahul Sharma, Soumya Banerjee, Dootika Vats, Piyush Rai
We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a flexible family of variational distributions.
no code implementations • 1 Jan 2021 • Rahul Sharma, Soumya Banerjee, Dootika Vats, Piyush Rai
Effective variational inference crucially depends on a flexible variational family of distributions.
no code implementations • 1 Jan 2021 • Soumya Banerjee, Vinay P Namboodiri
However, these methods mainly focus on incremental batch learning.
no code implementations • NeurIPS 2020 • Soumya Banerjee
In this work we study online rent-or-buy problems as a sequential decision making problem.
1 code implementation • 11 May 2020 • Soumya Banerjee, Debarshi Kumar Sanyal, Samiran Chattopadhyay, Plaban Kumar Bhowmick, Parthapratim Das
In the biomedical literature, it is customary to structure an abstract into discourse categories like BACKGROUND, OBJECTIVE, METHOD, RESULT, and CONCLUSION, but this segmentation is uncommon in other fields like computer science.
no code implementations • 21 Sep 2015 • Soumya Banerjee, Joshua Hecker
In this research we use a decentralized computing approach to allocate and schedule tasks on a massively distributed grid.
1 code implementation • 8 Aug 2010 • Soumya Banerjee, Melanie Moses
We find that a sub-modular NIS architecture, in which lymph node number and size both increase sublinearly with body size, efficiently balances the tradeoff between local pathogen detection and global response using antibodies.