Results 21 to 30 of about 124,788 (331)

Neural networks for modelling and control of a non-linear dynamic system [PDF]

open access: yes, 1992
The authors describe the use of neural nets to model and control a nonlinear second-order electromechanical model of a drive system with varying time constants and saturation effects. A model predictive control structure is used.
Murray-Smith, R.   +2 more
core   +1 more source

XNOR-Nets with SETs: Proposal for a binarised convolution processing elements with Single-Electron Transistors

open access: yesScientific Reports, 2022
Deep neural network (DNN) and Convolution neural network (CNN) algorithms have significantly increased the accuracies in cutting-edge large-scale image recognition and natural-language processing tasks.
Varun Bheemireddy
doaj   +1 more source

Solving SAT in linear time with a neural-like membrane system [PDF]

open access: yes, 2003
We present in this paper a neural-like membrane system solving the SAT problem in linear time. These neural Psystems are nets of cells working with multisets.
Pazos Sierra, Juan   +2 more
core   +2 more sources

Neuroinformatics I: Fuzzy Neural Networks of More-Equal-Less Logic (Static)

open access: yesInformatics in Education, 2004
This article analyzes the possibilities of neural nets composed of neurons - the summators of continuously varied impulse frequencies characterized by non-linearity {N}, when informational operations of fuzzy logic are performed.
Dobilas KIRVELIS, Girstaute DAGYTE
doaj   +1 more source

Uncovering Neural Learning Dynamics Through Latent Mutual Information

open access: yesEntropy
We study how convolutional neural networks reorganize information during learning in natural image classification tasks by tracking mutual information (MI) between inputs, intermediate representations, and labels. Across VGG-16, ResNet-18, and ResNet-50,
Arianna Issitt   +4 more
doaj   +1 more source

Brain inspired neuronal silencing mechanism to enable reliable sequence identification

open access: yesScientific Reports, 2022
Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes.
Shiri Hodassman   +7 more
doaj   +1 more source

Synaptic Hyaluronan Synthesis and CD44-Mediated Signaling Coordinate Neural Circuit Development

open access: yesCells, 2021
The hyaluronan-based extracellular matrix is expressed throughout nervous system development and is well-known for the formation of perineuronal nets around inhibitory interneurons.
Emily S. Wilson, Karen Litwa
doaj   +1 more source

Characterizing Satellite Geometry via Accelerated 3D Gaussian Splatting

open access: yesAerospace
The accelerating deployment of spacecraft in orbit has generated interest in on-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR).
Van Minh Nguyen   +3 more
doaj   +1 more source

Novel multi‐domain attention for abstractive summarisation

open access: yesCAAI Transactions on Intelligence Technology, 2023
The existing abstractive text summarisation models only consider the word sequence correlations between the source document and the reference summary, and the summary generated by models lacks the cover of the subject of source document due to models ...
Chunxia Qu   +4 more
doaj   +1 more source

Neural Proof Nets [PDF]

open access: yesProceedings of the 24th Conference on Computational Natural Language Learning, 2020
Linear logic and the linear -calculus have a long standing tradition in the study of natural language form and meaning. Among the proof calculi of linear logic, proof nets are of particular interest, offering an attractive geometric representation of derivations that is unburdened by the bureaucratic complications of conventional prooftheoretic ...
Kogkalidis, Konstantinos   +2 more
openaire   +3 more sources

Home - About - Disclaimer - Privacy