Eigen value based loss function for training attractors in iterated autoencoders
A Nouri, SA Seyyedsalehi - Neural Networks, 2023 - Elsevier
The way that the human brain handles the input variations has been one of the most
interesting areas of research for neuroscientists. There are some evidences that the human …
interesting areas of research for neuroscientists. There are some evidences that the human …
Modified deep attractor neural networks for variability compensation in recognition tasks
Some brain functions can be described with attractor formation in the human neural system.
Various biologically-inspired models have employed this characteristic for memory …
Various biologically-inspired models have employed this characteristic for memory …
Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks
N Alipour, SA SeyyedSalehi - arXiv preprint arXiv:2406.10579, 2024 - arxiv.org
The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical
concern for ensuring the suitability of deep neural networks in safety-critical systems …
concern for ensuring the suitability of deep neural networks in safety-critical systems …
Attractor manipulation in denoising autoencoders for robust phone recognition
S Reza, SA Seyyedsalehi… - 2021 29th Iranian …, 2021 - ieeexplore.ieee.org
Autoencoder Neural Networks can filter unwanted variabilities; however, their performance
will degrade if their attractors and their basins of attraction are not correctly adjusted. This …
will degrade if their attractors and their basins of attraction are not correctly adjusted. This …
[HTML][HTML] Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
S Reza, A Seyyedsalehi… - Signal and Data …, 2023 - jsdp.rcisp.ac.ir
Speech recognition is a subfield of artificial intelligence that develops technologies to
convert speech utterance into transcription. So far, various methods such as hidden Markov …
convert speech utterance into transcription. So far, various methods such as hidden Markov …
[HTML][HTML] اندازهگیری نسبتهای طلایی چهره با استفاده از مدل مبتنی بر رگرسیون آبشاری برای کاربرد در آنالیز زیبایی چهره
فهمی جعفرقلخانلو, شمسی - هوش محاسباتی در مهندسی برق, 2024 - isee.ui.ac.ir
: امروزه، جراحیهای پلاستیک چهره بهدلیل اصلاح نقصهای ناشی از مشکلات مادرزادی، ترمیم بافت
آسیبدیده از سوختگی و ایجاد ساختار زیبا در چهره بهطور چشمگیری افزایش یافته است …
آسیبدیده از سوختگی و ایجاد ساختار زیبا در چهره بهطور چشمگیری افزایش یافته است …
Why Dose Layer-by-Layer Pre-training Improve Deep Neural Networks Learning?
SZ Seyyedsalehi, SA Seyyedsalehi - Handbook of Deep Learning …, 2019 - Springer
Deep perceptron neural networks are capable of implementing a hierarchy of successive
nonlinear conversions. But training these neural networks by conventional learning methods …
nonlinear conversions. But training these neural networks by conventional learning methods …