Zobrazeno 1 - 10
of 14 833
pro vyhledávání: '"Chaudhry, A. P."'
Given a budget on total model size, one must decide whether to train a single, large neural network or to combine the predictions of many smaller networks. We study this trade-off for ensembles of random-feature ridge regression models. We prove that
Externí odkaz:
http://arxiv.org/abs/2412.05418
Autor:
Chaudhry, Zan
We introduce an algorithm for efficiently representing convolution with zero-padding and stride as a sparse transformation matrix, applied to a vectorized input through sparse matrix-vector multiplication (SpMV). We provide a theoretical contribution
Externí odkaz:
http://arxiv.org/abs/2411.19419
Autor:
Iskarous, Mark M., Chaudhry, Zan, Li, Fangjie, Bello, Samuel, Sankar, Sriramana, Slepyan, Ariel, Chugh, Natasha, Hunt, Christopher L., Greene, Rebecca J., Thakor, Nitish V.
Humans have an exquisite sense of touch which robotic and prosthetic systems aim to recreate. We developed algorithms to create neuron-like (neuromorphic) spiking representations of texture that are invariant to the scanning speed and contact force a
Externí odkaz:
http://arxiv.org/abs/2411.17060
ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks
Autor:
Chaudhry, Zan, Mizuno, Naoko
Hyperparameter tuning remains a significant challenge for the training of deep neural networks (DNNs), requiring manual and/or time-intensive grid searches, increasing resource costs and presenting a barrier to the democratization of machine learning
Externí odkaz:
http://arxiv.org/abs/2411.16975
Estimating building height from satellite imagery poses significant challenges, especially when monocular images are employed, resulting in a loss of essential 3D information during imaging. This loss of spatial depth further complicates the height e
Externí odkaz:
http://arxiv.org/abs/2411.09411
Autor:
Chaudhry, Hafsa, Patel, Hetvi, Avadhootha, Sai Teja, Poreddy, Sushanthik Reddy, Chollati, Swapan Gupta, Namineni, Ujwala, Ashqar, Huthaifa I.
Gender differences were examined in sensitivity to sleep quality, in the context of blue light exposure from smartphones. Our hypothesis was created based on our journal article findings that females are more prone to be inclined to the prolonged usa
Externí odkaz:
http://arxiv.org/abs/2411.02388
Physics-informed neural networks (PINN) is a machine learning (ML)-based method to solve partial differential equations that has gained great popularity due to the fast development of ML libraries in the last few years. The Poisson-Boltzmann equation
Externí odkaz:
http://arxiv.org/abs/2410.12810
Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these in
Externí odkaz:
http://arxiv.org/abs/2409.12180
Autor:
Chaudhry, Abraar, Rebrova, Elizaveta
We propose a flexible and theoretically supported framework for scalable nonnegative matrix factorization. The goal is to find nonnegative low-rank components directly from compressed measurements, accessing the original data only once or twice. We c
Externí odkaz:
http://arxiv.org/abs/2409.04994
Low-noise amplifiers are of great importance in the field of quantum technologies. We study a thermally driven parametric amplifier based on a superconductor-insulator-graphene-insulator-superconductor (SIGIS) junction coupled to a superconducting mi
Externí odkaz:
http://arxiv.org/abs/2408.11807