Results 81 to 90 of about 2,238,851 (367)
Selection dynamics for deep neural networks [PDF]
Journal of Differential Equations, 2020 27.
Liu, Hailiang, Markowich, Peter A.
openaire +4 more sources
Economic Structure Analysis Based on Neural Network and Bionic Algorithm
Complexity, 2021 In this article, an in-depth study and analysis of economic structure are carried out using a neural network fusion release algorithm. The method system defines the weight space and structure space of neural networks from the perspective of optimization ...
Yanjun Dai, Lin Su
doaj +1 more source
IEEE Access, 2023 The power system frequency is an important indicator that reflects the power system’s operating status. Through real-time detection or prediction, it can effectively ensure stable power system operation.
Wenzhuo Wang +8 more
doaj +1 more source
, 2018 We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4x4 Ising model. Using its success at this task, we motivate the study of the larger 8x8 Ising model, showing that the deep neural ...
Mills, Kyle, Tamblyn, Isaac
core +1 more source
Accelerating Deep Learning with Shrinkage and Recall
, 2016 Deep Learning is a very powerful machine learning model. Deep Learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large.
Ding, Chris +2 more
core +1 more source
Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction [PDF]
Italian National Conference on Sensors, 2017 This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and
Xiaolei Ma +5 more
semanticscholar +1 more source
Archetypal landscapes for deep neural networks [PDF]
Proceedings of the National Academy of Sciences, 2020 Significance Deep neural networks have reached impressive predictive capability for many challenging tasks, yet it remains unclear why they work. Training neural networks involves minimizing a complex, high-dimensional, nonconvex loss function, yet, empirically, it proves possible to produce useful models without rigorous global optimization.
Verpoort, Philipp C +2 more
openaire +3 more sources
Making tau amyloid models in vitro: a crucial and underestimated challenge
FEBS Letters, EarlyView.This review highlights the challenges of producing in vitro amyloid assemblies of the tau protein. We review how accurately the existing protocols mimic tau deposits found in the brain of patients affected with tauopathies. We discuss the important properties that should be considered when forming amyloids and the benchmarks that should be used to ...
Julien Broc, Clara Piersson, Yann Fichou
wiley +1 more source
Neural Network Architecture for EEG Based Speech Activity Detection
Acta Electrotechnica et Informatica, 2021 In this paper, research focused on speech activity detection using brain EEG signals is presented. In addition to speech stimulation of brain activity, an innovative approach based on the simultaneous stimulation of the brain by visual stimuli such as ...
Koctúrová Marianna, Juhár Jozef
doaj +1 more source
A Solution Method for Differential Equations Based on Taylor PINN
IEEE Access, 2023 Based on deep neural network, elliptic partial differential equations in complex regions are solved. Accurate and effective strategies and numerical methods for elliptic partial differential equations are proposed by implementing deep feedforward ...
Yajuan Zhang +3 more
doaj +1 more source