Zobrazeno 1 - 10
of 353
pro vyhledávání: '"P, Tipirneni"'
Autor:
Tipirneni, Sindhu, Adkathimar, Ravinarayana, Choudhary, Nurendra, Hiranandani, Gaurush, Amjad, Rana Ali, Ioannidis, Vassilis N., Yuan, Changhe, Reddy, Chandan K.
Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed that powerful closed-source LLMs provide good quality clusterings of ent
Externí odkaz:
http://arxiv.org/abs/2405.00988
Autor:
Ghaderi, Hamid, Foreman, Brandon, Nayebi, Amin, Tipirneni, Sindhu, Reddy, Chandan K., Subbian, Vignesh
Publikováno v:
AMIA Annu Symp Proc. 2024 Jan 11;2023:379-388
Determining clinically relevant physiological states from multivariate time series data with missing values is essential for providing appropriate treatment for acute conditions such as Traumatic Brain Injury (TBI), respiratory failure, and heart fai
Externí odkaz:
http://arxiv.org/abs/2303.13024
Autor:
Ghaderi, Hamid, Foreman, Brandon, Nayebi, Amin, Tipirneni, Sindhu, Reddy, Chandan K., Subbian, Vignesh
Self-supervised learning approaches provide a promising direction for clustering multivariate time-series data. However, real-world time-series data often include missing values, and the existing approaches require imputing missing values before clus
Externí odkaz:
http://arxiv.org/abs/2302.13457
Publikováno v:
Transactions on Machine Learning Research (TMLR), 2023
The utilization of programming language (PL) models, pre-trained on large-scale code corpora, as a means of automating software engineering processes has demonstrated considerable potential in streamlining various code generation tasks such as code c
Externí odkaz:
http://arxiv.org/abs/2301.13816
Unpacking and comprehending how black-box machine learning algorithms make decisions has been a persistent challenge for researchers and end-users. Explaining time-series predictive models is useful for clinical applications with high stakes to under
Externí odkaz:
http://arxiv.org/abs/2211.06507
A longstanding challenge surrounding deep learning algorithms is unpacking and understanding how they make their decisions. Explainable Artificial Intelligence (XAI) offers methods to provide explanations of internal functions of algorithms and reaso
Externí odkaz:
http://arxiv.org/abs/2208.06717
Autor:
Zhu, Ming, Jain, Aneesh, Suresh, Karthik, Ravindran, Roshan, Tipirneni, Sindhu, Reddy, Chandan K.
Recent advances in machine learning have significantly improved the understanding of source code data and achieved good performance on a number of downstream tasks. Open source repositories like GitHub enable this process with rich unlabeled code dat
Externí odkaz:
http://arxiv.org/abs/2206.08474
There has been a recent surge of interest in automating software engineering tasks using deep learning. This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language or a natu
Externí odkaz:
http://arxiv.org/abs/2206.05239
The distance matrix of a connected graph is defined as the matrix in which the entries are the pairwise distances between vertices. The distance spectrum of a graph is the set of eigenvalues of its distance matrix. A graph is said to be determined by
Externí odkaz:
http://arxiv.org/abs/2201.02499
Autor:
Tipirneni, Sindhu, Reddy, Chandan K.
Multivariate time-series data are frequently observed in critical care settings and are typically characterized by sparsity (missing information) and irregular time intervals. Existing approaches for learning representations in this domain handle the
Externí odkaz:
http://arxiv.org/abs/2107.14293