Results 51 to 60 of about 68,187 (284)

Sound Recognition System Using Spiking and MLP Neural Networks [PDF]

open access: yes, 2016
In this paper, we explore the capabilities of a sound classification system that combines a Neuromorphic Auditory System for feature extraction and an artificial neural network for classification.
Cerezuela Escudero, Elena   +5 more
core  

A parallel supercomputer implementation of a biological inspired neural network and its use for pattern recognition [PDF]

open access: yes, 2012
: A parallel implementation of a large spiking neural network is proposed and evaluated. The neural network implements the binding by synchrony process using the Oscillatory Dynamic Link Matcher (ODLM).
Bergeron, Jocelyn   +6 more
core   +1 more source

Gut microbiome and aging—A dynamic interplay of microbes, metabolites, and the immune system

open access: yesFEBS Letters, EarlyView.
Age‐dependent shifts in microbial communities engender shifts in microbial metabolite profiles. These in turn drive shifts in barrier surface permeability of the gut and brain and induce immune activation. When paired with preexisting age‐related chronic inflammation this increases the risk of neuroinflammation and neurodegenerative diseases.
Aaron Mehl, Eran Blacher
wiley   +1 more source

Live Demonstration: Neuromorphic Row-by-Row Multi-convolution FPGA Processor-SpiNNaker architecture for Dynamic-Vision Feature Extraction [PDF]

open access: yes, 2019
In this demonstration a spiking neural network architecture for vision recognition using an FPGA spiking convolution processor, based on leaky integrate and fire neurons (LIF) and a SpiNNaker board is presented.
Domínguez Morales, Juan Pedro   +5 more
core  

Stimulus sensitivity of a spiking neural network model [PDF]

open access: yes, 2017
Some recent papers relate the criticality of complex systems to their maximal capacity of information processing. In the present paper, we consider high dimensional point processes, known as age-dependent Hawkes processes, which have been used to model ...
Chevallier, Julien
core   +5 more sources

RIPK4 function interferes with melanoma cell adhesion and metastasis

open access: yesMolecular Oncology, EarlyView.
RIPK4 promotes melanoma growth and spread. RIPK4 levels increase as skin lesions progress to melanoma. CRISPR/Cas9‐mediated deletion of RIPK4 causes melanoma cells to form less compact spheroids, reduces their migratory and invasive abilities and limits tumour growth and dissemination in mouse models.
Norbert Wronski   +9 more
wiley   +1 more source

Hepatic encephalopathy detection using deep learning based optimized spiking neural network

open access: yesMeasurement: Sensors
Hepatic encephalopathy is caused by liver insufficiency or poor portal-systemic blood flow. In this work, a novel optimized spiking neural network (OSNN) is used to classify normal and HE cases by using CT images.
R.K. Shanmugha Priya, Dr K. Suthendran
doaj   +1 more source

Deep Spiking Neural Network model for time-variant signals classification: a real-time speech recognition approach [PDF]

open access: yes, 2018
Speech recognition has become an important task to improve the human-machine interface. Taking into account the limitations of current automatic speech recognition systems, like non-real time cloud-based solutions or power demand, recent interest for
Davidson, Simón   +6 more
core  

A generative spike train model with time-structured higher order correlations [PDF]

open access: yes, 2013
Emerging technologies are revealing the spiking activity in ever larger neural ensembles. Frequently, this spiking is far from independent, with correlations in the spike times of different cells.
Eric eShea-Brown   +4 more
core   +4 more sources

Spiking Neural Networks Trained via Proxy

open access: yesIEEE Access, 2022
We propose a new learning algorithm to train spiking neural networks (SNN) using conventional artificial neural networks (ANN) as proxy. We couple two SNN and ANN networks, respectively, made of integrate-and-fire (IF) and ReLU neurons with the same network architectures and shared synaptic weights.
Kheradpisheh, Saeed Reza   +2 more
openaire   +5 more sources

Home - About - Disclaimer - Privacy