Results 81 to 90 of about 876,297 (223)

Verifying Properties of Binarized Deep Neural Networks

, 2018
Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural ...
Kasiviswanathan, Shiva Prasad, Narodytska, Nina, Ryzhyk, Leonid, Sagiv, Mooly, Walsh, Toby   +4 more
core   +1 more source

Short-Term Load Forecasting of Natural Gas with Deep Neural Network Regression †

Energies, 2018
Deep neural networks are proposed for short-term natural gas load forecasting. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields such as image recognition and speech ...
Gregory D. Merkel, Richard J. Povinelli, Ronald H. Brown   +2 more
doaj   +1 more source

Gated Attention Recurrent Neural Network: A Deeping Learning Approach for Radar-Based Precipitation Nowcasting [PDF]

, 2022
Guanchen Wu, Wenhui Chen, Hoe-Kyung Jung
openalex   +1 more source

Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis

Physical Review Research
Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of deep learning.
Donghee Lee, Hye-Sung Lee, Jaeok Yi
doaj   +1 more source

A Systematic Exploration of Deep Neural Networks for EDA-Based Emotion Recognition

Information, 2020
Subject-independent emotion recognition based on physiological signals has become a research hotspot. Previous research has proved that electrodermal activity (EDA) signals are an effective data resource for emotion recognition.
Dian Yu, Shouqian Sun
doaj   +1 more source

Learning in Deep Radial Basis Function Networks

Entropy
Learning in neural networks with locally-tuned neuron models such as radial Basis Function (RBF) networks is often seen as instable, in particular when multi-layered architectures are used. Furthermore, universal approximation theorems for single-layered
Fabian Wurzberger, Friedhelm Schwenker
doaj   +1 more source

Random deep neural networks are biased towards simple functions

, 2019
We prove that the binary classifiers of bit strings generated by random wide deep neural networks with ReLU activation function are biased towards simple functions. The simplicity is captured by the following two properties.
De Palma, Giacomo, Kiani, Bobak Toussi, Lloyd, Seth   +2 more
core  

On Combining Deep Neural Network Classifiers for Source Device Identification

IEEE Access
This paper proposes combining deep neural network classifiers while simultaneously optimizing the networks. The proposed combination scheme enhances the accuracy of each classifier, which, in turn, boosts the overall combined accuracy during a post ...
Ioannis Tsingalis, Constantine Kotropoulos   +1 more
doaj   +1 more source

Deep Complex Networks

, 2018
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations.
Bengio, Yoshua, Bilaniuk, Olexa, Mehri, Soroush, Pal, Christopher J, Rostamzadeh, Negar, Santos, João Felipe, Serdyuk, Dmitriy, Subramanian, Sandeep, Trabelsi, Chiheb, Zhang, Ying   +9 more
core  

Spatiotemporal diffractive deep neural networks

Optics Express
A spatiotemporal diffractive deep neural network (STD2NN) is proposed for spatiotemporal signal processing. The STD2NN is formed by gratings, which convert the signal from the frequency domain to the spatial domain, and multiple layers consisting of spatial lenses and space light modulators (SLMs), which conduct spatiotemporal phase modulation.
Junhe Zhou, Haoqian Pu, Jiaxin Yan
openaire   +2 more sources