Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Sahu, Surya Kant"'
Autor:
Sahu, Surya Kant
Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks; otherwise,
Externí odkaz:
http://arxiv.org/abs/2210.06341
The Lottery Ticket Hypothesis (LTH) states that for a reasonably sized neural network, a sub-network within the same network yields no less performance than the dense counterpart when trained from the same initialization. This work investigates the r
Externí odkaz:
http://arxiv.org/abs/2206.08175
Autor:
Chopra, Ayush, Sahu, Surya Kant, Singh, Abhishek, Java, Abhinav, Vepakomma, Praneeth, Sharma, Vivek, Raskar, Ramesh
Distributed deep learning frameworks like federated learning (FL) and its variants are enabling personalized experiences across a wide range of web clients and mobile/IoT devices. However, FL-based frameworks are constrained by computational resource
Externí odkaz:
http://arxiv.org/abs/2112.01637
Transformers have seen an unprecedented rise in Natural Language Processing and Computer Vision tasks. However, in audio tasks, they are either infeasible to train due to extremely large sequence length of audio waveforms or incur a performance penal
Externí odkaz:
http://arxiv.org/abs/2109.10252
Session-based recommendation systems suggest relevant items to users by modeling user behavior and preferences using short-term anonymous sessions. Existing methods leverage Graph Neural Networks (GNNs) that propagate and aggregate information from n
Externí odkaz:
http://arxiv.org/abs/2107.01516
Benford's Law (BL) or the Significant Digit Law defines the probability distribution of the first digit of numerical values in a data sample. This Law is observed in many naturally occurring datasets. It can be seen as a measure of naturalness of a g
Externí odkaz:
http://arxiv.org/abs/2102.03313