Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Vibhav Gogate"'
Autor:
Chiradeep Roy, Mahsan Nourani, Donald R. Honeycutt, Jeremy E. Block, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract We consider the following activity recognition task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. This task can be solved using modern deep learning architectures based on neur
Externí odkaz:
https://doaj.org/article/56000094290e49ed902d912c15a5afec
Autor:
Mahsan Nourani, Chiradeep Roy, Jeremy E. Block, Donald R. Honeycutt, Tahrima Rahman, Eric D. Ragan, Vibhav Gogate
Publikováno v:
ACM Transactions on Interactive Intelligent Systems. 12:1-29
While EXplainable Artificial Intelligence (XAI) approaches aim to improve human-AI collaborative decision-making by improving model transparency and mental model formations, experiential factors associated with human users can cause challenges in way
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7cf05125c347dd36502e5d5971f8b062
https://doi.org/10.1145/3531066
https://doi.org/10.1145/3531066
DETOXER: A Visual Debugging Tool With Multiscope Explanations for Temporal Multilabel Classification
Publikováno v:
IEEE Computer Graphics and Applications. 42:37-46
In many applications, developed deep learning models need to be iteratively debugged and refined to improve the model efficiency over time. Debugging some models, like Temporal Multi-Label Classification (TMLC) where each datapoint can simultaneously
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83972cf4f5522401cef3ce76c5ccf21f
https://doi.org/10.1109/mcg.2022.3201465
https://doi.org/10.1109/mcg.2022.3201465
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 26:1910-1916
We consider lifted importance sampling (LIS), a previously proposed approximate inference algorithm for statistical relational learning (SRL) models. LIS achieves substantial variance reduction over conventional importance sampling by using various l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbf13d1f1f4f11161ec6056a461dce61
https://doi.org/10.1609/aaai.v26i1.8400
https://doi.org/10.1609/aaai.v26i1.8400
Autor:
Vibhav Gogate, Jeremy Block, Tahrima Rahman, Mahsan Nourani, Nicholas Ruozzi, Donald R. Honeycutt, Eric D. Ragan, Chiradeep Roy
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
We consider the following activity recognition task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. This task can be solved using modern deep learning architectures based on neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b056bcce775bb629b8f5dd9cb8699ab3
https://doaj.org/article/56000094290e49ed902d912c15a5afec
https://doaj.org/article/56000094290e49ed902d912c15a5afec
Autor:
Tahrima Rahman, Mahsan Nourani, Vibhav Gogate, Donald R. Honeycutt, Jeremy E. Block, Eric D. Ragan, Chiradeep Roy
Publikováno v:
IUI
EXplainable Artificial Intelligence (XAI) approaches are used to bring transparency to machine learning and artificial intelligence models, and hence, improve the decision-making process for their end-users. While these methods aim to improve human u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::806244d17eb17aeefe8a3fc982b54cd9
https://doi.org/10.1145/3397481.3450639
https://doi.org/10.1145/3397481.3450639
Investigating the Importance of First Impressions and Explainable AI with Interactive Video Analysis
Autor:
Jeremy E. Block, Vibhav Gogate, Tahrima Rahman, Mahsan Nourani, Chiradeep Roy, Donald R. Honeycutt, Eric D. Ragan
Publikováno v:
CHI Extended Abstracts
We present research on how the perception of intelligent systems can be influenced by early experiences of machine performance, and how explainability potentially helps users develop an accurate understanding of system capabilities. Using a custom vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::159f5d65f3526245da79089ec9484eba
https://doi.org/10.1145/3334480.3382967
https://doi.org/10.1145/3334480.3382967
Publikováno v:
IJCAI
Recently there has been growing interest in learning probabilistic models that admit poly-time inference called tractable probabilistic models from data. Although they generalize poorly as compared to intractable models, they often yield more accurat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8874c42c70bd42c16b68a3037853e131
https://doi.org/10.24963/ijcai.2019/797
https://doi.org/10.24963/ijcai.2019/797
Publikováno v:
IJCAI
We consider the following nearest assignment problem (NAP): given a Bayesian network B and probability value q, find a configuration w of variables in B such that difference between q and the probability of w is minimized. NAP is much harder than con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a6e31056a2172645b3ecdb0bc289c31
https://doi.org/10.24963/ijcai.2018/707
https://doi.org/10.24963/ijcai.2018/707
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
Parameter tying is a regularization method in which parameters (weights) of a machine learning model are partitioned into groups by leveraging prior knowledge and all parameters in each group are constrained to take the same value. In this paper, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04e83541ebb1431e779383f7d40418dc
https://doi.org/10.1609/aaai.v32i1.11785
https://doi.org/10.1609/aaai.v32i1.11785