Results 41 to 50 of about 68,095 (317)

Improving Spiking Neural Network Performance with Auxiliary Learning

Machine Learning and Knowledge Extraction, 2023
The use of back propagation through the time learning rule enabled the supervised training of deep spiking neural networks to process temporal neuromorphic data. However, their performance is still below non-spiking neural networks. Previous work pointed
Paolo G. Cachi, Sebastián Ventura, Krzysztof J. Cios   +2 more
doaj   +1 more source

Stochasticity from function -- why the Bayesian brain may need no noise [PDF]

, 2019
An increasing body of evidence suggests that the trial-to-trial variability of spiking activity in the brain is not mere noise, but rather the reflection of a sampling-based encoding scheme for probabilistic computing.
Baumbach, Andreas, Breitwieser, Oliver, Bytschok, Ilja, Dold, Dominik, Kungl, Akos F., Meier, Karlheinz, Petrovici, Mihai A., Schemmel, Johannes, Senn, Walter   +8 more
core   +2 more sources

Real Spike: Learning Real-Valued Spikes for Spiking Neural Networks

, 2022
Accepted by ...
Guo, Yufei, Zhang, Liwen, Chen, Yuanpei, Tong, Xinyi, Liu, Xiaode, Wang, YingLei, Huang, Xuhui, Ma, Zhe   +7 more
openaire   +2 more sources

Supervised Associative Learning in Spiking Neural Network [PDF]

, 2005
In this paper, we propose a simple supervised associative learning approach for spiking neural networks. In an excitatory-inhibitory network paradigm with Izhikevich spiking neurons, synaptic plasticity is implemented on excitatory to excitatory synapses
F. Crick, E.M. Izhikevich, E.M. Izhikevich, A. Kasinski, P. Dayan, N. Brunel, H. Paugam-Moisy   +6 more
core   +1 more source

Encountering Spiking Neural Networks

Visual Anthropology Review, 2023
AbstractOver the past two decades, the term “intelligent media” has surfaced to describe media that take on problematics of cognition, communication, and sensory perception loosely modeled after human intelligence. Taking the form of hardware‐software assemblages, these novel media demonstrate forms of autonomy that challenge human control and herald a
Alexandre Saunier, David Howes
openaire   +1 more source

Spiking Neural Network Pressure Sensor

Neural Computation
Abstract Von Neumann architecture requires information to be encoded as numerical values. For that reason, artificial neural networks running on computers require the data coming from sensors to be discretized. Other network architectures that more closely mimic biological neural networks (e.g., spiking neural networks) can be simulated ...
Markiewicz, Michał, Brzozowski, Ireneusz, Janusz, Szymon   +2 more
openaire   +3 more sources

Advancing Neural Networks: Innovations and Impacts on Energy Consumption

Advanced Electronic Materials
The energy efficiency of Artificial Intelligence (AI) systems is a crucial and actual issue that may have an important impact on an ecological, economic and technological level.
Alina Fedorova, Nikola Jovišić, Jordi Vallverdù, Silvia Battistoni, Miloš Jovičić, Milovan Medojević, Alexander Toschev, Evgeniia Alshanskaia, Max Talanov, Victor Erokhin   +9 more
doaj   +1 more source

Research on Anti-Interference Performance of Spiking Neural Network Under Network Connection Damage

Brain Sciences
Background: With the development of artificial intelligence, memristors have become an ideal choice to optimize new neural network architectures and improve computing efficiency and energy efficiency due to their combination of storage and computing ...
Yongqiang Zhang, Haijie Pang, Jinlong Ma, Guilei Ma, Xiaoming Zhang, Menghua Man   +5 more
doaj   +1 more source

Sparse Computation in Adaptive Spiking Neural Networks

Frontiers in Neuroscience, 2019
Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a computationally and ...
Davide Zambrano, Roeland Nusselder, H. Steven Scholte, Sander M. Bohté, Sander M. Bohté   +4 more
doaj   +1 more source

Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection

, 2020
Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires further power efficiency.
Cernak, Milos, Dellaferrera, Giorgia, Mainar, Pablo, Martinelli, Flavio   +3 more
core   +1 more source