Výsledky vyhledávání

Akademický článek

NEO: NEuro-Inspired Optimization—A Fractional Time Series Approach

Autor: Sarthak Chatterjee, Subhro Das, Sérgio Pequito

Publikováno v: Frontiers in Physiology, Vol 12 (2021)

Solving optimization problems is a recurrent theme across different fields, including large-scale machine learning systems and deep learning. Often in practical applications, we encounter objective functions where the Hessian is ill-conditioned, whic

Externí odkaz: https://doaj.org/article/b38707dfa2ab4d9b8cfdb45a2161e22c

Zobrazit plný text záznamu

GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models

Autor: Farzan Farnia, William W. Wang, Subhro Das, Ali Jadbabaie

Publikováno v: SIAM Journal on Mathematics of Data Science. 5:122-146

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8fb9d1bea0b904022fbb9cf68b79b21f
https://doi.org/10.1137/21m1445831

Zobrazit plný text záznamu

Learning skills adjacency representations for optimized reskilling recommendations

Autor: Saksham Gandhi, Raj Nagesh, Subhro Das

Publikováno v: 2022 IEEE International Conference on Big Data (Big Data).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3c1ba17cbd7a29c0e44add541a9739a6
https://doi.org/10.1109/bigdata55660.2022.10020405

Zobrazit plný text záznamu

On observability and optimal gain design for distributed linear filtering and prediction

Autor: Subhro Das

This paper presents a new approach to distributed linear filtering and prediction. The problem under consideration consists of a random dynamical system observed by a multi-agent network of sensors where the network is sparse. Inspired by the consens

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::edbea7064c4df0b9efd1f78dd543a06d

Zobrazit plný text záznamu

Evaluating Robustness of Cooperative MARL: A Model-based Approach

Autor: Pham, Nhan H., Nguyen, Lam M., Chen, Jie, Lam, Hoang Thanh, Subhro Das, Tsui-Wei Weng

In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evalua

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fdce3e8b1c7a60641a7515657aa867f

Zobrazit plný text záznamu

On Multisensor Activation Policies for Bernoulli Tracking

Autor: Augustin A. Saucan, Subhro Das, Moe Z. Win

Publikováno v: MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::60039e3e99b35e0db02f3e4bb376f363
https://doi.org/10.1109/milcom52596.2021.9652984

Zobrazit plný text záznamu

An Adaptive, Data-Driven Personalized Advisor for Increasing Physical Activity

Autor: Subhro Das, Ching-Hua Chen, Chandramouli Maduri, Kun Lin, James Codella, Tian Hao, Zhiguo Li

Publikováno v: IEEE Journal of Biomedical and Health Informatics. 23:999-1010

In recent years, there has been growing interest in the use of fitness trackers and smartphone applications for promoting physical activity. Many of these applications use accelerometers to estimate the level of activity that users engage in and prov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8bf595045700c660f4105002519eaf7
https://doi.org/10.1109/jbhi.2018.2879805

Zobrazit plný text záznamu

Verifiably Safe Exploration for End-to-End Reinforcement Learning

Autor: Nathan Fulton, Subhro Das, Nathan Hunt, Armando Solar-Lezama, Trong Nghia Hoang, Sara Magliacane

Publikováno v: HSCC2021: proceedings of the 24th International Conference on Hybrid Systems: Computation and Control (part of CPS-IoT Week) : May 19-21, 2021, Nashville, TN, USA
HSCC2021
HSCC

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end policies

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43fecda33c9d4ad61513f0bd78d544e8
https://dare.uva.nl/personal/pure/en/publications/verifiably-safe-exploration-for-endtoend-reinforcement-learning(e4605542-c419-4304-bd2a-0d4e4dc12dbb).html

Zobrazit plný text záznamu

A Research Framework for Understanding Education-Occupation Alignment with NLP Techniques

Autor: Carlos Lastra-Anadon, Subhro Das, Kush R. Varshney, Renzhe Yu, Hari Raghavan, Sairam Gurajada

Publikováno v: Proceedings of the 1st Workshop on NLP for Positive Impact.

Understanding the gaps between job requirements and university curricula is crucial for improving student success and institutional effectiveness in higher education. In this context, natural language processing (NLP) can be leveraged to generate gra

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::183cc7924bdc315974fb9b2675abde30
https://doi.org/10.18653/v1/2021.nlp4posimpact-1.11

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání