Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Hodassman, Shiri"'
Publikováno v:
Physica A, Statistical Mechanics and its Applications (2024), 130166
Significant variations of delays among connecting neurons cause an inevitable disadvantage of asynchronous brain dynamics compared to synchronous deep learning. However, this study demonstrates that this disadvantage can be converted into a computati
Externí odkaz:
http://arxiv.org/abs/2410.11384
Publikováno v:
Scientific Reports volume 14, Article number: 5881 (2024)
Recently, the underlying mechanism for successful deep learning (DL) was presented based on a quantitative method that measures the quality of a single filter in each layer of a DL model, particularly VGG-16 trained on CIFAR-10. This method exemplifi
Externí odkaz:
http://arxiv.org/abs/2309.07537
Autor:
Tzach, Yarden, Meir, Yuval, Tevet, Ofek, Gross, Ronit D., Hodassman, Shiri, Vardi, Roni, Kanter, Ido
Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the existing deep l
Externí odkaz:
http://arxiv.org/abs/2305.18078
Publikováno v:
Sci Rep 13, 962 (2023)
Advanced deep learning architectures consist of tens of fully connected and convolutional hidden layers, currently extended to hundreds, are far from their biological realization. Their implausible biological dynamics relies on changing a weight in a
Externí odkaz:
http://arxiv.org/abs/2211.11378
Publikováno v:
Sci Rep 13, 5423 (2023)
The realization of complex classification tasks requires training of deep learning (DL) architectures consisting of tens or even hundreds of convolutional and fully connected hidden layers, which is far from the reality of the human brain. According
Externí odkaz:
http://arxiv.org/abs/2211.11106
Autor:
Meir, Yuval, Sardi, Shira, Hodassman, Shiri, Kisos, Karin, Ben-Noam, Itamar, Goldental, Amir, Kanter, Ido
Publikováno v:
Sci Rep 10, 19628 (2020)
Power-law scaling, a central concept in critical phenomena, is found to be useful in deep learning, where optimized test errors on handwritten digit examples converge as a power-law to zero with database size. For rapid decision making with one train
Externí odkaz:
http://arxiv.org/abs/2211.08430
Autor:
Hodassman, Shiri, Meir, Yuval, Kisos, Karin, Ben-Noam, Itamar, Tugendhaft, Yael, Goldental, Amir, Vardi, Roni, Kanter, Ido
Publikováno v:
Sci Rep 12, 16003 (2022)
Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes. Existing methods apply recurrent neural networks, which suffer from training diffic
Externí odkaz:
http://arxiv.org/abs/2203.13028
Autor:
Koresh, Ella, Halevi, Tal, Meir, Yuval, Dilmoney, Dolev, Dror, Tamar, Gross, Ronit, Tevet, Ofek, Hodassman, Shiri, Kanter, Ido
Publikováno v:
In Physica A: Statistical Mechanics and its Applications 15 July 2024 646
Autor:
Tevet, Ofek, Gross, Ronit D., Hodassman, Shiri, Rogachevsky, Tal, Tzach, Yarden, Meir, Yuval, Kanter, Ido
Publikováno v:
In Physica A: Statistical Mechanics and its Applications 1 February 2024 635
Autor:
Sardi, Shira, Vardi, Roni, Meir, Yuval, Tugendhaft, Yael, Hodassman, Shiri, Goldental, Amir, Kanter, Ido
Publikováno v:
Scientific Reports 10, Article number: 6923 (2020) https://www.nature.com/articles/s41598-020-63755-5
Attempting to imitate the brain functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning. Here, using neuronal c
Externí odkaz:
http://arxiv.org/abs/2005.04106