Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Pratik Chaudhari"'
Autor:
Ronald W. DiTullio, Chetan Parthiban, Eugenio Piasini, Pratik Chaudhari, Vijay Balasubramanian, Yale E. Cohen
Publikováno v:
Frontiers in Computational Neuroscience, Vol 17 (2023)
Sensory systems appear to learn to transform incoming sensory information into perceptual representations, or “objects,” that can inform and guide behavior with minimal explicit supervision. Here, we propose that the auditory system can achieve t
Externí odkaz:
https://doaj.org/article/c36f543436da47599f983b09d6cf48d4
Publikováno v:
Entropy, Vol 22, Iss 1, p 101 (2020)
This paper is a step towards developing a geometric understanding of a popular algorithm for training deep neural networks named stochastic gradient descent (SGD). We built upon a recent result which observed that the noise in SGD while training typi
Externí odkaz:
https://doaj.org/article/21d83ed6dd34421083c9cbde1cc87a9e
Publikováno v:
Proceedings of the National Academy of Sciences. 120
Despite the great promise that machine learning has offered in many fields of medicine, it has also raised concerns about potential biases and poor generalization across genders, age distributions, races and ethnicities, hospitals, and data acquisiti
Occam's razor is the principle that, all else being equal, simpler explanations should be preferred over more complex ones. This principle is thought to play a role in human perception and decision-making, but the nature of our presumed preference fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04e5ac029f4fd3e66ceec939ea01f681
https://doi.org/10.1101/2023.01.10.523479
https://doi.org/10.1101/2023.01.10.523479
Autor:
Pratik Chaudhari, Dinesh Thakur, Avi Cohen, Ty Nguyen, Ian D. Miller, Vijay Kumar, Shashank Prasad, Arjun Guru, Camillo J. Taylor
Publikováno v:
IEEE Robotics and Automation Letters. 6:5032-5039
Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100 000 4K images of more than 20 types of micro aerial vehicles (MAVs). The dataset can b
Autor:
Sourabh Suke, Ganesh Regulwar, Nikesh Aote, Pratik Chaudhari, Rajat Ghatode, Mahima Pimple, Vishakha Bijekar
Publikováno v:
International Journal of Advanced Research in Science, Communication and Technology. :156-159
This project describes "VoiEmo- A Speech Emotion Recognizer", a system for recognizing the emotional state of an individual from his/her speech. For example, one's speech becomes loud and fast, with a higher and wider range in pitch, when in a state
Publikováno v:
Innovation in Aging. 6:253-253
Vulnerable older adults benefit from community-based telehealth programs (CTP) that facilitate remote health monitoring with support from trained personnel. This study assessed acceptability with such technology as a self-reported measure of comfort
Autor:
Fanyang Yu, Anahita Fathi Kazerooni, Erik Toorens, Hamed Akbari, Chiharu Sako, Elizabeth Mamourian, Stephen Bagley, Zev A Binder, Robert A Lustig, Steven Brem, Donald M O’Rourke, Tapan Ganguly, Spyridon Bakas, MacLean Nasrallah, Pratik Chaudhari, Christos Davatzikos
Publikováno v:
Neuro-Oncology. 24:vii166-vii166
PURPOSE There is evidence that molecular heterogeneity of glioblastoma is associated with heterogeneity of MR imaging signatures. Modern machine learning models, such as deep neural networks, provide a tool for capturing such complex relationships in
Autor:
Anirudh Cowlagi, Pratik Chaudhari
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:12931-12932
This paper studies the over-parameterization of deep neural networks using the Fisher Information Matrix from information geometry. We identify several surprising trends in the structure of its eigenspectrum, and how this structure relates to the eig
Publikováno v:
ICRA
We propose a framework for deformable linear object prediction. Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimensional configuration spaces. By mapping the dynamics from a non-linear spa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7837e7201e947f266046553825908c14