scholarly journals A Survey of Encoding Techniques for Signal Processing in Spiking Neural Networks

2021 ◽  
Author(s):  
Daniel Auge ◽  
Julian Hille ◽  
Etienne Mueller ◽  
Alois Knoll
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Industrial Applications ◽  
Spiking Neural Networks ◽  
Biologically Inspired ◽  
Power Efficient ◽  
Signal Encoding ◽  
Uniform Nomenclature ◽  
Theoretical Foundations ◽  
Do So

AbstractBiologically inspired spiking neural networks are increasingly popular in the field of artificial intelligence due to their ability to solve complex problems while being power efficient. They do so by leveraging the timing of discrete spikes as main information carrier. Though, industrial applications are still lacking, partially because the question of how to encode incoming data into discrete spike events cannot be uniformly answered. In this paper, we summarise the signal encoding schemes presented in the literature and propose a uniform nomenclature to prevent the vague usage of ambiguous definitions. Therefore we survey both, the theoretical foundations as well as applications of the encoding schemes. This work provides a foundation in spiking signal encoding and gives an overview over different application-oriented implementations which utilise the schemes.

scholarly journals The POEtic Electronic Tissue and Its Role in the Emulation of Large-Scale Biologically Inspired Spiking Neural Networks Models

Complexus ◽  
2006 ◽  
Vol 3 (1-3) ◽  
pp. 32-47 ◽  
Author(s):  
J.Manuel Moreno ◽  
Yann Thoma ◽  
Eduardo Sanchez ◽  
Jan Eriksson ◽  
Javier Iglesias ◽  
...  
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Spiking Neural Networks ◽  
Biologically Inspired

scholarly journals Modelling an Adaptive Learning System Using Artificial Intelligence

Webology ◽  
2021 ◽  
Vol 19 (1) ◽  
pp. 01-18
Author(s):  
Hayder Rahm Dakheel AL-Fayyadh ◽  
Salam Abdulabbas Ganim Ali ◽  
Dr. Basim Abood
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Adaptive Learning ◽  
Back Propagation ◽  
Learning System ◽  
Spiking Neural Networks ◽  
Domain Specific Language ◽  
Domain Specific ◽  
Adaptive Learning System ◽  
Artificial Neural

The goal of this paper is to use artificial intelligence to build and evaluate an adaptive learning system where we adopt the basic approaches of spiking neural networks as well as artificial neural networks. Spiking neural networks receive increasing attention due to their advantages over traditional artificial neural networks. They have proven to be energy efficient, biological plausible, and up to 105 times faster if they are simulated on analogue traditional learning systems. Artificial neural network libraries use computational graphs as a pervasive representation, however, spiking models remain heterogeneous and difficult to train. Using the artificial intelligence deductive method, the paper posits two hypotheses that examines whether 1) there exists a common representation for both neural networks paradigms for tutorial mentoring, and whether 2) spiking and non-spiking models can learn a simple recognition task for learning activities for adaptive learning. The first hypothesis is confirmed by specifying and implementing a domain-specific language that generates semantically similar spiking and non-spiking neural networks for tutorial mentoring. Through three classification experiments, the second hypothesis is shown to hold for non-spiking models, but cannot be proven for the spiking models. The paper contributes three findings: 1) a domain-specific language for modelling neural network topologies in adaptive tutorial mentoring for students, 2) a preliminary model for generalizable learning through back-propagation in spiking neural networks for learning activities for students also represented in results section, and 3) a method for transferring optimised non-spiking parameters to spiking neural networks has also been developed for adaptive learning system. The latter contribution is promising because the vast machine learning literature can spill-over to the emerging field of spiking neural networks and adaptive learning computing. Future work includes improving the back-propagation model, exploring time-dependent models for learning, and adding support for adaptive learning systems.

Compact Hardware Synthesis of Stochastic Spiking Neural Networks

2019 ◽  
Vol 29 (08) ◽  
pp. 1950004 ◽  
Author(s):  
Fabio Galán-Prado ◽  
Alejandro Morán ◽  
Joan Font ◽  
Miquel Roca ◽  
Josep L. Rosselló
Keyword(s):  
Neural Networks ◽  
Processing Speed ◽  
Back Propagation ◽  
High Volume ◽  
High Density ◽  
Digital Design ◽  
Spiking Neural Networks ◽  
Biologically Inspired ◽  
Proposed Model ◽  
Technical Interest

Spiking neural networks (SNN) are able to emulate real neural behavior with high confidence due to their bio-inspired nature. Many designs have been proposed for the implementation of SNN in hardware, although the realization of high-density and biologically-inspired SNN is currently a complex challenge of high scientific and technical interest. In this work, we propose a compact digital design for the implementation of high-volume SNN that considers the intrinsic stochastic processes present in biological neurons and enables high-density hardware implementation. The proposed stochastic SNN model (SSNN) is compared with previous SSNN models, achieving a higher processing speed. We also show how the proposed model can be scaled to high-volume neural networks trained by using back propagation and applied to a pattern classification task. The proposed model achieves better results compared with other recently-published SNN models configured with unsupervised STDP learning.

Deep learning asan advanced concept of artificial intelligence

2018 ◽  
Vol 9 (1) ◽  
pp. 15-18
Author(s):  
Megha Gupta1 ◽  
Jitender Rai
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Learning Community ◽  
Traditional Learning ◽  
Biologically Inspired ◽  
Computing Power ◽  
Challenging Tasks ◽  
Widespread Availability ◽  
Temporary Memory

This paper represented on the Deep learning technique growing in the learning community of machines, as traditional learning architecture has proven incompetent for the machine learning challenging tasks and strong feature of artificial intelligence (AI). Increasing and widespread availability of computing power, along the use of efficient training and improvement algorithms, has made it possible to implement, until then, the concept of deep learning. These development events deep learning architecture and algorithms look at cognitive neuroscience and point to biologically inspired solutions for learning. This paper represented on the rule of Convolutional Neural Networks (CNNs), Neural Networks (SNNs) and Hierarchical Temporary Memory (HTM), and other related techniques to the least mature technique.

ПРОЦЕССОРЫ, ПАМЯТЬ И ПРОГРАММНОЕ ОБЕСПЕЧЕНИЕ ДЛЯ ЭФФЕКТИВНОЙ РЕАЛИЗАЦИИ НЕЙРОННЫХ СЕТЕЙ

2020 ◽  
Vol 96 (3s) ◽  
pp. 580-584
Author(s):  
О.А. Тельминов ◽  
Е.С. Горнев ◽  
Г.С. Теплов
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
State Of The Art ◽  
Spiking Neural Networks ◽  
Third Generation ◽  
The Third

Рассмотрен ландшафт искусственного интеллекта (ИИ) в области реализации перспективных нейронных сетей третьего поколения - спайковых нейронных сетей. Выявлены закономерности в принципах построения современной элементной базы и дана оценка возможности развития перспективной элементной базы. Предложен вариант встраивания деятельности компании в существующую экосистему ИИ. The paper considers the emerging landscape of artificial intelligence in the field of the third generation spiking neural networks. Some patterns principles of modern hardware components have been discovered, as well as possibilities of advanced components development. The Company’s ways of incorporation into state-of-the-art artificial intelligence ecosystem has been proposed.

Sign in / Sign up

Export Citation Format

Share Document