Evolving spiking neural networks for online learning over drifting data streams
Nowadays huge volumes of data are produced in the form of fast streams, which are further
affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of …
affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of …
Anytime multipurpose emotion recognition from EEG data using a Liquid State Machine based framework
Recent technological advances in machine learning offer the possibility of decoding
complex datasets and discern latent patterns. In this study, we adopt Liquid State Machines …
complex datasets and discern latent patterns. In this study, we adopt Liquid State Machines …
Salient detection via the fusion of background-based and multiscale frequency-domain features
S Song, Z Jia, J Yang, N Kasabov - Information Sciences, 2022 - Elsevier
Salient object detection is a fundamental problem in image processing and computer vision.
Many saliency detection algorithms based on the background and frequency-domain are …
Many saliency detection algorithms based on the background and frequency-domain are …
Classification and regression of spatio-temporal signals using NeuCube and its realization on SpiNNaker neuromorphic hardware
Objective. The objective of this work is to use the capability of spiking neural networks to
capture the spatio-temporal information encoded in time-series signals and decode them …
capture the spatio-temporal information encoded in time-series signals and decode them …
Prediction and detection of virtual reality induced cybersickness: a spiking neural network approach using spatiotemporal EEG brain data and heart rate variability
AHX Yang, NK Kasabov, YO Cakmak - Brain informatics, 2023 - Springer
Virtual Reality (VR) allows users to interact with 3D immersive environments and has the
potential to be a key technology across many domain applications, including access to a …
potential to be a key technology across many domain applications, including access to a …
Brain-inspired spiking neural networks
Brain is a very efficient computing system. It performs very complex tasks while occupying
about 2 liters of volume and consuming very little energy. The computation tasks are …
about 2 liters of volume and consuming very little energy. The computation tasks are …
Evolving and spiking connectionist systems for brain-inspired artificial intelligence
N Kasabov - Artificial intelligence in the age of neural networks and …, 2019 - Elsevier
Artificial neural networks have now a long history as major techniques in computational
intelligence with a wide range of application for learning from data and for artificial …
intelligence with a wide range of application for learning from data and for artificial …
FROM MULTILAYER PERCEPTRONS AND NEUROFUZZY SYSTEMS TO DEEP LEARNING MACHINES: WHICH METHOD TO USE?-A SURVEY.
N Kasabov - … Journal on Information Technologies & Security, 2017 - search.ebscohost.com
Artificial neural networks have now a long history as major techniques in computational
intelligence with a wide range of application for learning from data. There are many methods …
intelligence with a wide range of application for learning from data. There are many methods …
[PDF][PDF] Neuroinformatics, Neural Networks and Neurocomputers for Computational Intelligence.
NK Kasabov - Neuroinformatics, 2023 - conf.uni-obuda.hu
1. Learning from (big) data-> neural networks and deep NN 2. Explainability (extracting
rules, associations)(explainable AI)→ fuzzy logic/neuro-fuzzy systems 3. Evolvability→ …
rules, associations)(explainable AI)→ fuzzy logic/neuro-fuzzy systems 3. Evolvability→ …
Sleep stage classification using neucube on spinnaker: a preliminary study
This paper studies sleep stage classification using NeuCube, a Spiking Neural Network
(SNN) architecture, simulated on SpiNNaker, a neuromorphic computer. The sleep …
(SNN) architecture, simulated on SpiNNaker, a neuromorphic computer. The sleep …