evt_MNIST: A spike based version of traditional MNIST an event-based MNIST

Fatahi, Mazdak; Shahsavari, Mahyar; Ahmadi, Mahmood; Ahmadi, Arash; Devienne, Philippe

Document type :

Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes

Title :

evt_MNIST: A spike based version of traditional MNIST an event-based MNIST

Author(s) :

Fatahi, Mazdak [Auteur]
Razi University of Kermanshah
Shahsavari, Mahyar [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Ahmadi, Mahmood [Auteur]
Razi University of Kermanshah
Ahmadi, Arash [Auteur]
Razi University of Kermanshah
Devienne, Philippe [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Conference title :

1st International Conference on New Research Achievements in Electrical and Computer Engineering

City :

Teheran

Country :

Iran

Start date of the conference :

2016-05-26

English keyword(s) :

Neuromorphic
spike train
Spiking Neural Networks
AER
Poisson distribution

HAL domain(s) :

Informatique [cs]/Informatique et langage [cs.CL]
Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

Benchmarks and datasets have important role in evaluation of machine learning algorithms and neural network implementations. Traditional dataset for images such as MNIST is applied to evaluate efficiency of different ...
Show more >Benchmarks and datasets have important role in evaluation of machine learning algorithms and neural network implementations. Traditional dataset for images such as MNIST is applied to evaluate efficiency of different training algorithms in neural networks. This demand is different in Spiking Neural Networks (SNN) as they require spiking inputs. It is widely believed, in the biological cortex the timing of spikes is irregular. Poisson distributions provide adequate descriptions of the irregularity in generating appropriate spikes. Here, we introduce a spike-based version of MNSIT (handwritten digits dataset), using Poisson distribution and show the Poissonian property of the generated streams. We introduce a new version of evt_MNIST which can be used for neural network evaluation.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.archives-ouvertes.fr/hal-01382631/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01382631/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01382631/document
Open access
Access the document

document
Open access
Access the document

evtMNIST_MazdakFatahi.pdf
Open access
Access the document

evt_MNIST: A spike based version of ... BibTeX CSV Excel RIS

Files

evt_MNIST: A spike based version of ...

BibTeX

CSV

Excel

RIS