Improving STDP-based Visual Feature Learning with Whitening

Falez, Pierre; Tirilly, Pierre; Bilasco, Ioan Marius

doi:10.1109/ijcnn48605.2020.9207373

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A transformation can be used to enhance features of the input signal (image) before the neural coding process [32]- [34]. This results in highlighted features having higher intensities and appearing in earlier time steps, meaning more excitation.…”

Section: Feature Enhancementmentioning

confidence: 99%

“…5) Zero-phase Component Analysis: Final implemented layer is zero-phase component analysis (ZCA) Whitening. It has been suggested [34] that this transformation can improve the accuracy of SNNs on real-world images. Spyker implements an efficient version of ZCA whitening by taking advantage of routines from highly optimized linear algebra libraries (BLAS and LAPACK) that operate on symmetric matrices.…”

Section: Feature Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

Spyker: High-performance Library for Spiking Deep Neural Networks

Shirsavar¹,

Dehaqani²

2023

Preprint

View full text Add to dashboard Cite

Spiking neural networks (SNNs) have been recently brought to light due to their promising capabilities. SNNs simulate the brain with higher biological plausibility compared to previous generations of neural networks. Learning with fewer samples and consuming less power are among the key features of these networks. However, the theoretical advantages of SNNs have not been seen in practice due to the slowness of simulation tools and the impracticality of the proposed network structures. In this work, we implement a high-performance library named Spyker using C++/CUDA from scratch that outperforms its predecessor. Several SNNs are implemented in this work with different learning rules (spike-timing-dependent plasticity and reinforcement learning) using Spyker that achieve significantly better runtimes, to prove the practicality of the library in the simulation of large-scale networks. To our knowledge, no such tools have been developed to simulate large-scale spiking neural networks with high performance using a modular structure. Furthermore, a comparison of the represented stimuli extracted from Spyker to recorded electrophysiology data is performed to demonstrate the applicability of SNNs in describing the underlying neural mechanisms of the brain functions. The aim of this library is to take a significant step toward uncovering the true potential of the brain computations using SNNs.

show abstract

Section: Feature Enhancementmentioning

confidence: 99%

Section: Feature Enhancementmentioning

confidence: 99%