Zobrazeno 1 - 10
of 15 590
pro vyhledávání: '"Filipovich"'
Autor:
Filipovich, Matthew J., Lvovsky, A. I.
TorchOptics is an open-source Python library for differentiable Fourier optics simulations, developed using PyTorch to enable GPU-accelerated tensor computations and automatic differentiation. It provides a comprehensive framework for modeling, analy
Externí odkaz:
http://arxiv.org/abs/2411.18591
Optical training of large-scale Transformers and deep neural networks with direct feedback alignment
Autor:
Wang, Ziao, Müller, Kilian, Filipovich, Matthew, Launay, Julien, Ohana, Ruben, Pariente, Gustave, Mokaadi, Safa, Brossollet, Charles, Moreau, Fabien, Cappelli, Alessandro, Poli, Iacopo, Carron, Igor, Daudet, Laurent, Krzakala, Florent, Gigan, Sylvain
Modern machine learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly considered for inference but, to date, remain mostly limited to rela
Externí odkaz:
http://arxiv.org/abs/2409.12965
Autor:
Buckley, Andy, Corpe, Louie, Filipovich, Matthew, Gutschow, Christian, Rozinsky, Nick, Thor, Simon, Yeh, Yoran, Yellen, Jamie
Histogramming is often taken for granted, but the power and compactness of partially aggregated, multidimensional summary statistics, and their fundamental connection to differential and integral calculus make them formidable statistical objects, esp
Externí odkaz:
http://arxiv.org/abs/2312.15070
Diffractive optical neural networks (DONNs) have emerged as a promising optical hardware platform for ultra-fast and energy-efficient signal processing for machine learning tasks, particularly in computer vision. Previous experimental demonstrations
Externí odkaz:
http://arxiv.org/abs/2310.03679
Autor:
Hanks, Patrick, Lenarčič, Simon
Publikováno v:
Dictionary of American Family Names, 2 ed., 2022.
Externí odkaz:
http://www.oxfordreference.com/view/10.1093/acref/9780190245115.001.0001/acref-9780190245115-e-24126
Alternatives to backpropagation have long been studied to better understand how biological brains may learn. Recently, they have also garnered interest as a way to train neural networks more efficiently. By relaxing constraints inherent to backpropag
Externí odkaz:
http://arxiv.org/abs/2210.14593
Autor:
Bardelli, L., Zhang, C., Bustos, E., Arnosio, M., Becchio, R., Filipovich, R., Viramonte, J., Lucci, F.
Publikováno v:
In Journal of South American Earth Sciences 1 February 2025 152
Publikováno v:
Pediatric Blood & Cancer. 67
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::059aa52f7d623ec9d04eeb5ccf153f42
https://doi.org/10.1002/pbc.28510
https://doi.org/10.1002/pbc.28510
Autor:
Filipovich, Matthew J., Guo, Zhimu, Al-Qadasi, Mohammed, Marquez, Bicky A., Morison, Hugh D., Sorger, Volker J., Prucnal, Paul R., Shekhar, Sudip, Shastri, Bhavin J.
Publikováno v:
Optica 9, 1323-1332 (2022)
There has been growing interest in using photonic processors for performing neural network inference operations; however, these networks are currently trained using standard digital electronics. Here, we propose on-chip training of neural networks en
Externí odkaz:
http://arxiv.org/abs/2111.06862
Autor:
Hanebutte, Ulf, Baldwin, Andrew, Durakovic, Senad, Filipovich, Igor, Chien-Chun, Chou, Adamowicz, Damian, Chickles, Derek, Hawkes, David
This paper presents a methodology to separate the quantization process from the hardware-specific model compilation stage via a pre-quantized deep learning model description in standard ONNX format. Separating the quantization process from the model
Externí odkaz:
http://arxiv.org/abs/2110.01730