Proceedings ArticleDOI
A population coding hardware architecture for Spiking Neural Networks applications
Marco Aurelio Nuño-Maganda,Miguel Arias-Estrada,Cesar Torres Huitzil,Bernard Girau +3 more
- pp 83-88
TLDR
The proposed hardware core is the first step for implementing successfully classifiers like SpikeProp algorithm and can be useful for data classifying and clustering applications, because this coding scheme has been used in the past and an efficient mapping of this technique in hardware can improve the actual performance of these applications.Abstract:
Recently, Spiking Neural Networks (SNNs) have obtained the interest of Machine Learning researchers due to the rich dynamics shown by these information processing models. One of the most important problems that must be addressed for implementing efficient SNNs is the information encoding. In this paper, an implementation of a high-performance hardware architecture for population information coding based on Gaussian Receptive Fields (GRFs) is proposed. This architecture can be useful for data classifying and clustering applications, because this coding scheme has been used in the past, and an efficient mapping of this technique in hardware can improve the actual performance of these applications. The GRFs information coding can be efficiently implemented on FPGA technology, because it contains several operations that can be computed in parallel like the exponential function. The proposed hardware architecture was implemented, tested and validated with several random datasets. The proposed hardware core is the first step for implementing successfully classifiers like SpikeProp algorithm. Synthesis and timing results for the proposed hardware architecture are presented.read more
Citations
More filters
Posted Content
Neural-like computing with populations of superparamagnetic basis functions
Alice Mizrahi,Tifenn Hirtzlin,Akio Fukushima,Hitoshi Kubota,Shinji Yuasa,Julie Grollier,Damien Querlioz +6 more
TL;DR: In this paper, a hybrid magnetic-CMOS system based on interlinked populations of junctions is proposed to realize non-linear variability-resilient transformations with a low imprint area and low power.
Dissertation
Stochastic magnetic tunnel junctions for bioinspired computing
TL;DR: An analogy between superparamagnetic tunnel junctions and sensory neurons which fire voltage pulses with random time intervals is drawn and it is demonstrated that populations of junctions can represent probability distributions and perform Bayesian inference.
Une méthode de machine à état liquide pour la classification de séries temporelles : A new liquid state machine method for temporal classification
TL;DR: A method that exploits the recent advances in computational neuroscience is presented: the liquid state machine, a biologically inspired computational model that aims at learning on input stimuli that outperform the conventional liquid statemachine approach.
Proceedings ArticleDOI
Spiking neural network applications
Gaffari Çelik,M. Fatih Talu +1 more
TL;DR: Artificial learning systems which can learn by using basic logical operators such as AND, OR, XOR have been developed in order to understand SNN structure.
Posted Content
Bio-inspired intelligent sensory processing with nanoscale stochastic magnetic tunnel junctions.
TL;DR: This study shows the feasibility of this intelligent bio-inspired sensory system as well as its robustness to device variability and its low energy consumption, opening the path to experimental realizations.
References
More filters
Journal ArticleDOI
Hardware/software co-design
G. De Michell,Rajesh Gupta +1 more
TL;DR: Co-design issues and their relationship to classical system implementation tasks are discussed to help develop a perspective on modern digital system design that relies on computer aided design (CAD) tools and methods.
Journal Article
Unsupervised clustering with spiking neurons by sparse temporal coding and multi-layer RBF networks
TL;DR: A temporal encoding of continuously valued data to obtain adjustable clustering capacity and precision with an efficient use of neurons is developed and encoded in a population code by neurons with graded and overlapping sensitivity profiles.
Journal ArticleDOI
Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks
TL;DR: In this paper, a spiking neural network based on spike-time coding and Hebbian learning is proposed for unsupervised clustering on real-world data, and temporal synchrony in a multilayer network can induce hierarchical clustering.
Proceedings ArticleDOI
Hardware-software partitioning in embedded system design
TL;DR: An ILP (integer linear programming) based approach is presented that are solving the problem optimally even for quite big systems, and a genetic algorithm that finds near-optimal solutions for even larger systems.
Journal ArticleDOI
Hardware-software codesign
TL;DR: System engineers must become knowledgeable in both hardware and software to successfully assimilate this new approach to systems design, Hardware-software codesign.