Results 21 to 30 of about 5,846,406 (312)
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 +4 more sources
Evolving Deep Neural Networks [PDF]
, 2019 The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution.
Risto Miikkulainen +10 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
Deep neural networks in psychiatry [PDF]
Molecular Psychiatry, 2019 Machine and deep learning methods, today's core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments ("big data"), and have started to find their way into ...
Daniel, Durstewitz +2 more
openaire +2 more sources
Deep Randomized Neural Networks [PDF]
, 2020 Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network architectures where the connections to the hidden layer(s) are left untrained after initialization.
Gallicchio C., Scardapane S.
openaire +4 more sources
Explaining deep neural networks
CoRR, 2020 Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users.
openaire +5 more sources
On Numerosity of Deep Neural Networks
CoRR, 2020 Accepted to NeurIPS ...
Xi Zhang 0019, Xiaolin Wu 0001
openaire +3 more sources
Enhanced gradient learning for deep neural networks
IET Image Processing, 2022 Deep neural networks have achieved great success in both computer vision and natural language processing tasks. How to improve the gradient flows is crucial in training very deep neural networks. To address this challenge, a gradient enhancement approach
Ming Yan +5 more
doaj +1 more source
An exact mapping from ReLU networks to spiking neural networks
, 2023 Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge.
Wulfram Gerstner +11 more
core +1 more source
Biotechnology Reports, 2019 Background: Deep neural networks have been successfully applied to diverse fields of computer vision. However, they only outperform human capacities in a few cases.
Antoine Buetti-Dinh +11 more
doaj +1 more source