Neural networks : the official journal of the International Neural Network Society
Feb 4, 2022
We consider restricted Boltzmann machine (RBMs) trained over an unstructured dataset made of blurred copies of definite but unavailable "archetypes" and we show that there exists a critical sample size beyond which the RBM can learn archetypes, namel...
Nature communications
Feb 1, 2022
Social interactions powerfully impact the brain and the body, but high-resolution descriptions of these important physical interactions and their neural correlates are lacking. Currently, most studies rely on labor-intensive methods such as manual an...
Journal of biophotonics
Jan 25, 2022
To accurately identify the blood authenticity, a set of photoacoustic detection system was established. In experiments, five kinds of blood in total of 125 groups were used, the time-resolved photoacoustic signals and peak-to-peak spectra were obtain...
ISA transactions
Jan 24, 2022
In order to solve a challenging problem, i.e., fixed time synchronization of bilayer networks with derivative coupling and nonlinear delay coupling, fixed time polices are brought to achieve random synchronization for bilayer multiple weight hybrid c...
Journal of biological physics
Jan 21, 2022
The nerve cells are responsible for transmitting messages through the action potential, which generates electrical stimulation. One of the methods and tools of electrical stimulation is infrared neural stimulation (INS). Since the mechanism of INS is...
Small (Weinheim an der Bergstrasse, Germany)
Jan 20, 2022
One of the important steps for realizing artificial intelligence is identifying elementary units that are beneficial for neural network construction. A type of memristive behavior in which phase-change nanoclusters nucleate adaptively in two adjacent...
Sensors (Basel, Switzerland)
Jan 18, 2022
In the last years, materializations of neuromorphic circuits based on nanophotonic arrangements have been proposed, which contain complete optical circuits, laser, photodetectors, photonic crystals, optical fibers, flat waveguides and other passive o...
IEEE transactions on cybernetics
Jan 11, 2022
Deep convolutional neural networks (CNNs) have demonstrated impressive performance on many visual tasks. Recently, they became useful models for the visual system in neuroscience. However, it is still not clear what is learned by CNNs in terms of neu...
Sensors (Basel, Switzerland)
Jan 7, 2022
Current developments in artificial olfactory systems, also known as electronic nose (e-nose) systems, have benefited from advanced machine learning techniques that have significantly improved the conditioning and processing of multivariate feature-ri...
PLoS computational biology
Jan 7, 2022
Task-optimized convolutional neural networks (CNNs) show striking similarities to the ventral visual stream. However, human-imperceptible image perturbations can cause a CNN to make incorrect predictions. Here we provide insight into this brittleness...