Výsledky vyhledávání - "Guillaume Bellec"

Akademický článek

High-performance deep spiking neural networks with 0.3 spikes per neuron

Autor: Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec, Giovanni Cherubini, Angeliki Pantazi, Wulfram Gerstner

Publikováno v: Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)

Abstract Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that th

Externí odkaz: https://doaj.org/article/232a98336e0941d79563834bb5c1b24e

Zobrazit plný text záznamu

Akademický článek

Fast learning without synaptic plasticity in spiking neural networks

Autor: Anand Subramoney, Guillaume Bellec, Franz Scherr, Robert Legenstein, Wolfgang Maass

Publikováno v: Scientific Reports, Vol 14, Iss 1, Pp 1-15 (2024)

Abstract Spiking neural networks are of high current interest, both from the perspective of modelling neural networks of the brain and for porting their fast learning capability and energy efficiency into neuromorphic hardware. But so far we have not

Externí odkaz: https://doaj.org/article/9d29cb0b7ea84a149d86f74757173287

Zobrazit plný text záznamu

Plný text ve formátu HTML

Akademický článek

Healthcare-associated adverse events and readmission to the emergency departments within seven days after a first consultation

Autor: Guillaume Gasperini, Leila Bouazzi, Antoine Sanchez, Louis Marotte, Laury Kézachian, Guillaume Bellec, Nicolas Cazes, Maxime Rosetti, Claire Bousquet, Aurélien Renard, Stéphane Sanchez

Publikováno v: Frontiers in Public Health, Vol 11 (2023)

IntroductionThe use of emergency hospital service has become increasingly frequent with a rise of approximately 3.6%. in annual emergency department visits. The objective of this study was to describe the reasons for reconsultations to emergency depa

Externí odkaz: https://doaj.org/article/bd75edddbfbf4e2298b91e84a2420bdd

Zobrazit plný text záznamu

Akademický článek

A solution to the learning dilemma for recurrent networks of spiking neurons

Autor: Guillaume Bellec, Franz Scherr, Anand Subramoney, Elias Hajek, Darjan Salaj, Robert Legenstein, Wolfgang Maass

Publikováno v: Nature Communications, Vol 11, Iss 1, Pp 1-15 (2020)

Bellec et al. present a mathematically founded approximation for gradient descent training of recurrent neural networks without backwards propagation in time. This enables biologically plausible training of spike-based neural network models with work

Externí odkaz: https://doaj.org/article/7910940bc2a3480f8457777933723618

Zobrazit plný text záznamu

Akademický článek

Spike frequency adaptation supports network computations on temporally dispersed information

Autor: Darjan Salaj, Anand Subramoney, Ceca Kraisnikovic, Guillaume Bellec, Robert Legenstein, Wolfgang Maass

Publikováno v: eLife, Vol 10 (2021)

For solving tasks such as recognizing a song, answering a question, or inverting a sequence of symbols, cortical microcircuits need to integrate and manipulate information that was dispersed over time during the preceding seconds. Creating biological

Externí odkaz: https://doaj.org/article/68ec1b19721b44b59bb32d6cc8654aac

Zobrazit plný text záznamu

Akademický článek

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

Autor: Chen Liu, Guillaume Bellec, Bernhard Vogginger, David Kappel, Johannes Partzsch, Felix Neumärker, Sebastian Höppner, Wolfgang Maass, Steve B. Furber, Robert Legenstein, Christian G. Mayr

Publikováno v: Frontiers in Neuroscience, Vol 12 (2018)

The memory requirement of deep learning algorithms is considered incompatible with the memory restriction of energy-efficient hardware. A low memory footprint can be achieved by pruning obsolete connections or reducing the precision of connection str

Externí odkaz: https://doaj.org/article/960a8bcfa5b240f2ba77185073583505

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání