Results 51 to 60 of about 827,210 (276)

Deep oscillatory neural network

Scientific Reports
We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscillatory activity.
Nurani Rajagopal Rohan, Vigneswaran C, Sayan Ghosh, Kishore Rajendran, Gaurav A, V. Srinivasa Chakravarthy   +5 more
openaire   +4 more sources

Deep Neural Networks and PIDE Discretizations

SIAM Journal on Mathematics of Data Science, 2022
In this paper, we propose neural networks that tackle the problems of stability and field-of-view of a Convolutional Neural Network (CNN). As an alternative to increasing the network's depth or width to improve performance, we propose integral-based spatially nonlocal operators which are related to global weighted Laplacian, fractional Laplacian and ...
Bastian Bohn, Michael Griebel, Dinesh Kannan   +2 more
openaire   +3 more sources

Geometric robustness of deep networks: analysis and improvement

, 2017
Deep convolutional neural networks have been shown to be vulnerable to arbitrary geometric transformations. However, there is no systematic method to measure the invariance properties of deep networks to such transformations.
Frossard, Pascal, Kanbak, Can, Moosavi-Dezfooli, Seyed-Mohsen   +2 more
core   +1 more source

Deep Morphological Neural Networks

CoRR, 2019
Mathematical morphology is a theory and technique to collect features like geometric and topological structures in digital images. Given a target image, determining suitable morphological operations and structuring elements is a cumbersome and time-consuming task.
Yucong Shen, Xin Zhong, Frank Y. Shih
openaire   +2 more sources

Implicit Saliency In Deep Neural Networks [PDF]

2020 IEEE International Conference on Image Processing (ICIP), 2020
In this paper, we show that existing recognition and localization deep architectures, that have not been exposed to eye tracking data or any saliency datasets, are capable of predicting the human visual saliency. We term this as implicit saliency in deep neural networks.
Yutong Sun, Mohit Prabhushankar, Ghassan AlRegib   +2 more
openaire   +2 more sources

Every Local Minimum Value is the Global Minimum Value of Induced Model in Non-convex Machine Learning

, 2019
For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any differentiable point. As a result, nonconvex machine learning is theoretically
Huang, Jiaoyang, Kaelbling, Leslie Pack, Kawaguchi, Kenji   +2 more
core   +1 more source

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

, 2017
Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their ...
C Barrett, C Barrett, D Silver, G Dantzig, G Hinton, I Goodfellow, J Kuchar, J Marques-Silva, J-B Jeannin, L Pulina, L Pulina, M Kochenderfer, M Kochenderfer, M Padberg, M Riesenhuber, R Nieuwenhuis, R Vanderbei   +16 more
core   +1 more source

Operator compression with deep neural networks

Advances in Continuous and Discrete Models, 2022
AbstractThis paper studies the compression of partial differential operators using neural networks. We consider a family of operators, parameterized by a potentially high-dimensional space of coefficients that may vary on a large range of scales. Based on the existing methods that compress such a multiscale operator to a finite-dimensional sparse ...
Kröpfl, Fabian, Maier, Roland, Peterseim, Daniel   +2 more
openaire   +3 more sources

Dynamic slicing for deep neural networks [PDF]

Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020
Program slicing has been widely applied in a variety of software engineering tasks. However, existing program slicing techniques only deal with traditional programs that are constructed with instructions and variables, rather than neural networks that are composed of neurons and synapses.
Ziqi Zhang, Yuanchun Li, Yao Guo 0001, Xiangqun Chen, Yunxin Liu   +4 more
openaire   +2 more sources

Reciprocal control of viral infection and phosphoinositide dynamics

FEBS Letters, EarlyView.
Phosphoinositides, although scarce, regulate key cellular processes, including membrane dynamics and signaling. Viruses exploit these lipids to support their entry, replication, assembly, and egress. The central role of phosphoinositides in infection highlights phosphoinositide metabolism as a promising antiviral target.
Marie Déborah Bancilhon, Bruno Mesmin
wiley   +1 more source