NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data

By Nikola K. Kasabov. 2014

435 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

1. German Ignacio Parisi
2. Stefan Wermter
3. Maryam Gholami Doborjeh
4. Zohreh Gholami Doborjeh
5. S. R. Kheradpisheh
6. Catherine D. Schuman
7. J. Parker Mitchell
8. Bill Kay

In Electrical and Electronic Engineering

1. Maryam Gholami Doborjeh
2. Zohreh Gholami Doborjeh
3. S. R. Kheradpisheh
4. Shruti R. Kulkarni
5. J. Parker Mitchell
6. Bill Kay
7. Maryam Parsa
8. Prasanna Date

Citations in the corpus

• Deep learning in neural networks: An overview (2014, neutral): “…2000; Deco & Rolls, 2005; Gerstner & Kistler, 2002; Gerstner & van Hemmen, 1992; Hoerzer, Legenstein, & Maass, 2014; Izhikevich et al., 2003; Kasabov, 2014; Kempter, Gerstner, & Van Hemmen, 1999; Kistler, Gerstner, & van Hemmen, 1997; Maass, 1996, 1997; Maex & Orban, 1996; Nessler,…”
• Lifelong learning of human actions with deep neural network self-organization (2017, background): “…using spiking neural networks have been proposed in which spatiotemporal information is encoded as locations of synapses and neurons taking into account the time of their spiking activity (Buonomano & Maass, 2009; Kasabov, 2014; Kasabov, Doborjeh, & Doborjeh, 2017; Zenke, Agnes, & Gerstner, 2015).”
• Mapping, Learning, Visualization, Classification, and Understanding of fMRI Data in the NeuCube Evolving Spatiotemporal Data Machine of Spiking Neural Networks (2017, methodology): “At the same time, the brain-inspired spiking neural network (SNN) models and their neuromorphic highly parallel implementations are advancing very fast [1], [12]–[14], [18]–[25].”
• Deep Learning in Spiking Neural Networks (2018, background): “The neuromorphic cube (NewCube) (Kasabov, 2014; Paulun, Wendt, & Kasabov, 2018; Schliebs, Hamed, & Kasabov, 2011) is a broad and futuristic model proposed as a unifying computational architecture for modeling multi-modality spatiotemporal data, most especially data related to the brain, such as EEG ”
• Opportunities for neuromorphic computing algorithms and applications (2022, methodology): “Combinations of spiking reservoirs and STDP have also been employed in an SNN approach called NeuCube 70 , which has been used to process electroencephalo-grams and functional magnetic resonance imaging signals in applications such as sleep state detection and prosthetic controllers 70–72 .”
• Making Sense of Spatio-Temporal Preserving Representations for EEG-Based Human Intention Recognition (2020, background): “Kasabov [51] proposed a 3-”