Memory-Efficient Synaptic Connectivity for Spike-Timing- Dependent Plasticity

Autor: Bruno U. Pedroni, Siddharth Joshi, Stephen R. Deiss, Sadique Sheik, Georgios Detorakis, Somnath Paul, Charles Augustine, Emre O. Neftci, Gert Cauwenberghs

Publikováno v: Frontiers in Neuroscience, Vol 13 (2019)

Spike-Timing-Dependent Plasticity (STDP) is a bio-inspired local incremental weight update rule commonly used for online learning in spike-based neuromorphic systems. In STDP, the intensity of long-term potentiation and depression in synaptic efficac

Externí odkaz: https://doaj.org/article/b867aac7b7094b1b98a14a510b0f78fb

Sustainable computational science: the ReScience initiative

Autor: Nicolas P. Rougier, Konrad Hinsen, Frédéric Alexandre, Thomas Arildsen, Lorena A. Barba, Fabien C.Y. Benureau, C. Titus Brown, Pierre de Buyl, Ozan Caglayan, Andrew P. Davison, Marc-André Delsuc, Georgios Detorakis, Alexandra K. Diem, Damien Drix, Pierre Enel, Benoît Girard, Olivia Guest, Matt G. Hall, Rafael N. Henriques, Xavier Hinaut, Kamil S. Jaron, Mehdi Khamassi, Almar Klein, Tiina Manninen, Pietro Marchesi, Daniel McGlinn, Christoph Metzner, Owen Petchey, Hans Ekkehard Plesser, Timothée Poisot, Karthik Ram, Yoav Ram, Etienne Roesch, Cyrille Rossant, Vahid Rostami, Aaron Shifman, Joseph Stachelek, Marcel Stimberg, Frank Stollmeier, Federico Vaggi, Guillaume Viejo, Julien Vitay, Anya E. Vostinar, Roman Yurchak, Tiziano Zito

Publikováno v: PeerJ Computer Science, Vol 3, p e142 (2017)

Computer science offers a large set of tools for prototyping, writing, running, testing, validating, sharing and reproducing results; however, computational science lags behind. In the best case, authors may provide their source code as a compressed

Externí odkaz: https://doaj.org/article/55a5db62f618401cbb64c77165d3988b

Randomized Self Organizing Map

Autor: Georgios Detorakis, Nicolas P. Rougier

Publikováno v: Neural Computation
Neural Computation, Massachusetts Institute of Technology Press (MIT Press), In press
Neural Computation, inPress, ⟨10.1162/neco_a_01406⟩

We propose a variation of the self organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess rando

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35dc0915c2ce6899e24f9ca7539e405d

ISS-Stabilization of Delayed Neural Fields by Small-Gain Arguments

Autor: Antoine Chaillet, Stéphane Palfi, Georgios Detorakis, Suhan Senova

Publikováno v: Delays and Interconnections: Methodology, Algorithms and Applications ISBN: 9783030115531

This chapter addresses the robust stabilization of neuronal populations modeled as delayed neural fields. These models are integro-differential equations representing the spatio-temporal activity of cerebral structures and take into account the non-i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1fec85f38f30f3f66bb84dd27742d62a
https://doi.org/10.1007/978-3-030-11554-8_5

Contrastive Hebbian Learning with Random Feedback Weights

Autor: Travis Bartley, Emre Neftci, Georgios Detorakis

Publikováno v: Detorakis, G; Bartley, T; & Neftci, E. (2018). Contrastive Hebbian Learning with Random Feedback Weights. UC Irvine: Retrieved from: http://www.escholarship.org/uc/item/4039t7rx

Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence algorithm. It op

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::051f04944faf59812a1218614bfc512f
http://www.escholarship.org/uc/item/4039t7rx