Ponencia
Learning weights with STDP to build prototype images for classification
Autor/es | Vasudevan, Ajay
Serrano Gotarredona, María Teresa Linares Barranco, Bernabé |
Departamento | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores |
Fecha de publicación | 2019 |
Fecha de depósito | 2020-10-22 |
Publicado en |
|
ISBN/ISSN | 978-1-7281-3424-6 |
Resumen | The combination of Spike Timing Dependent Plasticity
(STDP) and latency coding used in a spiking neural network
has been shown to learn hierarchical features. In this paper we
propose a new way to classify images using ... The combination of Spike Timing Dependent Plasticity (STDP) and latency coding used in a spiking neural network has been shown to learn hierarchical features. In this paper we propose a new way to classify images using an SVM. Prototype images are built from the weights learned in an unsupervised manner using STDP. The prototype images are cross correlated with the input image and the peak of the cross correlation with each prototype image is used as additional features for an SVM. The network, demonstrated on the MNIST data set, achieves 99.15% testing accuracy which is the best reported accuracy for a SNN with unsupervised training. |
Agencias financiadoras | European Union (UE) European Union (UE) Ministerio de Economía y Competitividad (MINECO). España |
Identificador del proyecto | Horizon 2020 No 687299 NeuRAM
Horizon 2020 No 824164 HERMES TEC2015-63884- C2-1-P |
Cita | Vasudevan, A., Serrano Gotarredona, M.T. y Linares Barranco, B. (2019). Learning weights with STDP to build prototype images for classification. En DTIS 2019: 14th International Conference on Design amd Technology of Integrated Systems In Nanoscale Era Mykonos, Greece: IEEE Computer Society. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Learning weights with STDP.pdf | 164.5Kb | [PDF] | Ver/ | |