Results 11 to 20 of about 827,210 (276)
Evolutional deep neural network [PDF]
Physical Review E, 2021 The notion of an Evolutional Deep Neural Network (EDNN) is introduced for the solution of partial differential equations (PDE). The parameters of the network are trained to represent the initial state of the system only, and are subsequently updated dynamically, without any further training, to provide an accurate prediction of the evolution of the PDE
Yifan Du, Tamer A. Zaki
openaire +3 more sources
Deep Polynomial Neural Networks [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). Code: https://github.com/grigorisg9gr/polynomial_nets.
Grigorios G. Chrysos +5 more
openaire +4 more sources
Deep Neural Networks as Complex Networks
CoRR, 2022 Deep Neural Networks are, from a physical perspective, graphs whose `links` and `vertices` iteratively process data and solve tasks sub-optimally. We use Complex Network Theory (CNT) to represents Deep Neural Networks (DNNs) as directed weighted graphs: within this framework, we introduce metrics to study DNNs as dynamical systems, with a granularity ...
Emanuele La Malfa +4 more
openaire +2 more sources
Deep Neural Networks for Network Routing [PDF]
2019 International Joint Conference on Neural Networks (IJCNN), 2019 In this work, we propose a Deep Learning (DL) based solution to the problem of routing traffic flows in computer networks. Routing decisions can be made in different ways depending on the desired objective and, based on that objective function, optimal solutions can be computed using a variety of techniques, e.g.
Reis, João +5 more
openaire +2 more sources
Tweaking Deep Neural Networks [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 Deep neural networks are trained so as to achieve a kind of the maximum overall accuracy through a learning process using given training data. Therefore, it is difficult to fix them to improve the accuracies of specific problematic classes or classes of interest that may be valuable to some users or applications.
Jinwook Kim +2 more
openaire +3 more sources
A new deep neural network for forecasting: Deep dendritic artificial neural network
Artificial Intelligence Review, 2023 Abstract Deep artificial neural networks have become a good alternative to classical forecasting methods in solving forecasting problems. Popular deep neural networks classically use additive aggregation functions in their cell structures.
Egrioglu, Erol, Bas, Eren
openaire +2 more sources
Topology of deep neural networks
J. Mach. Learn. Res., 2020 We study how the topology of a data set $M = M_a \cup M_b \subseteq \mathbb{R}^d$, representing two classes $a$ and $b$ in a binary classification problem, changes as it passes through the layers of a well-trained neural network, i.e., with perfect accuracy on training set and near-zero generalization error ($\approx 0.01\%$). The goal is to shed light
Gregory Naitzat +2 more
openaire +4 more sources
Orthogonal Deep Neural Networks [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 In this paper, we introduce the algorithms of Orthogonal Deep Neural Networks (OrthDNNs) to connect with recent interest of spectrally regularized deep learning methods. OrthDNNs are theoretically motivated by generalization analysis of modern DNNs, with the aim to find solution properties of network weights that guarantee better generalization.
Shuai Li +4 more
openaire +3 more sources
Statistical physics of deep neural networks: Initialization toward optimal channels
Physical Review Research, 2023 In deep learning, neural networks serve as noisy channels between input data and its latent representation. This perspective naturally relates deep learning with the pursuit of constructing channels with optimal performance in information transmission ...
Kangyu Weng +4 more
doaj +1 more source
Fast Sparse Deep Neural Networks: Theory and Performance Analysis
IEEE Access, 2019 In this paper, fast sparse deep neural networks that aim to offer an alternative way of learning in a deep structure are proposed. We examine some optimization algorithms for traditional deep neural networks and find that deep neural networks suffer from
Jin Zhao, Licheng Jiao
doaj +1 more source