Results 71 to 80 of about 876,297 (223)

Non-attracting Regions of Local Minima in Deep and Wide Neural Networks

, 2020
Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications.
Petzka, Henning, Sminchisescu, Cristian
core  

An Analysis of the Connections Between Layers of Deep Neural Networks [PDF]

, 2013
We present an analysis of different techniques for selecting the connection be- tween layers of deep neural networks. Traditional deep neural networks use ran- dom connection tables between layers to keep the number of connections small and tune to ...
Bates, Jordan, Culurciello, Eugenio, Dundar, Aysegul, Jin, Jonghoon   +3 more
core  

Prediction of local elasto-plastic stress and strain fields in a two-phase composite microstructure using a deep convolutional neural network [PDF]

, 2023
Indrashish Saha, Ashwini Gupta, Lori Graham‐Brady   +2 more
openalex   +1 more source

Two-Stage Approach to Image Classification by Deep Neural Networks

EPJ Web of Conferences, 2018
The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying.
Ososkov Gennady, Goncharov Pavel
doaj   +1 more source

Variants of RMSProp and Adagrad with Logarithmic Regret Bounds [PDF]

, 1960
Adaptive gradient methods have become recently very popular, in particular as they have been shown to be useful in the training of deep neural networks. In this paper we have analyzed RMSProp, originally proposed for the training of deep neural networks,
Mukkamala, Mahesh Chandra, Hein, Matthias   +1 more
core   +3 more sources

A unified framework for Hamiltonian deep neural networks [PDF]

, 2021
Clara Lucía Galimberti, Liang Xu, Giancarlo Ferrari‐Trecate   +2 more
openalex   +1 more source

Deep Neural Network or Dermatologist? [PDF]

, 2019
Deep learning techniques have proven high accuracy for identifying melanoma in digitised dermoscopic images. A strength is that these methods are not constrained by features that are pre-defined by human semantics. A down-side is that it is difficult to understand the rationale of the model predictions and to identify potential failure modes. This is a
Young, Kyle, Booth, Gareth, Simpson, Becks, Dutton, Reuben, Shrapnel, Sally   +4 more
openaire   +2 more sources

Deep learning in spiking neural networks [PDF]

Neural Networks, 2019
In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation.
Kheradpisheh, Saeed Reza, Tavanaei, Amirhossein, Ghodrati, Masoud, Kheradpisheh, Saeed Reza, Masquelier, Timothée, Maida, Anthony   +5 more
openaire   +3 more sources

Deep neural networks and humans both benefit from compositional language structure

Nature Communications
Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings.
Lukas Galke, Yoav Ram, Limor Raviv
doaj   +1 more source

Low-Resource Cross-Domain Product Review Sentiment Classification Based on a CNN with an Auxiliary Large-Scale Corpus

Algorithms, 2017
The literature [-5]contains several reports evaluating the abilities of deep neural networks in text transfer learning. To our knowledge, however, there have been few efforts to fully realize the potential of deep neural networks in cross-domain product ...
Xiaocong Wei, Hongfei Lin, Yuhai Yu, Liang Yang   +3 more
doaj   +1 more source