Zobrazeno 1 - 10
of 1 208
pro vyhledávání: '"Gupta, Gopal A."'
Machine learning models are increasingly used in critical areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, as individuals need explanations to underst
Externí odkaz:
http://arxiv.org/abs/2410.22615
Autor:
Murugesan, Anitha, Wong, Isaac, Arias, Joaquín, Stroud, Robert, Varadarajan, Srivatsan, Salazar, Elmer, Gupta, Gopal, Bloomfield, Robin, Rushby, John
Assurance cases offer a structured way to present arguments and evidence for certification of systems where safety and security are critical. However, creating and evaluating these assurance cases can be complex and challenging, even for systems of m
Externí odkaz:
http://arxiv.org/abs/2408.11699
Autor:
Vašíček, Ondřej, Arias, Joaquin, Fiedor, Jan, Gupta, Gopal, Hall, Brendan, Křena, Bohuslav, Larson, Brian, Varanasi, Sarat Chandra, Vojnar, Tomáš
This paper proposes a new methodology for early validation of high-level requirements on cyber-physical systems with the aim of improving their quality and, thus, lowering chances of specification errors propagating into later stages of development w
Externí odkaz:
http://arxiv.org/abs/2408.09909
Autor:
Zeng, Yankai, Rajashekharan, Abhiramon, Basu, Kinjal, Wang, Huaduo, Arias, Joaquín, Gupta, Gopal
The development of large language models (LLMs), such as GPT, has enabled the construction of several socialbots, like ChatGPT, that are receiving a lot of attention for their ability to simulate a human conversation. However, the conversation is not
Externí odkaz:
http://arxiv.org/abs/2407.18498
Machine learning models are increasingly used in areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, and individuals need explanations to understand deci
Externí odkaz:
http://arxiv.org/abs/2407.08179
Autor:
Wang, Huaduo, Gupta, Gopal
We present a novel and systematic method, called Superfast Selection, for selecting the "optimal split" for decision tree and feature selection algorithms over tabular data. The method speeds up split selection on a single feature by lowering the tim
Externí odkaz:
http://arxiv.org/abs/2405.20622
Recent efforts in interpreting Convolutional Neural Networks (CNNs) focus on translating the activation of CNN filters into a stratified Answer Set Program (ASP) rule-sets. The CNN filters are known to capture high-level image concepts, thus the pred
Externí odkaz:
http://arxiv.org/abs/2405.15886
Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable
Externí odkaz:
http://arxiv.org/abs/2402.04382
Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable to revea
Externí odkaz:
http://arxiv.org/abs/2310.14497
Autor:
Padalkar, Parth, Gupta, Gopal
Within the realm of deep learning, the interpretability of Convolutional Neural Networks (CNNs), particularly in the context of image classification tasks, remains a formidable challenge. To this end we present a neurosymbolic framework, NeSyFOLD-G t
Externí odkaz:
http://arxiv.org/abs/2310.13073