Development of GUI Flow Editor Supporting Neuromorphic Architecture Based Neural Network

Amorphous Computational Material (ACM) is a concept of an active material that can sense its environment and, due to its cognitive capabilities, react “intelligently” to those changes. In this paper, We demonstrate the feasibility of utilizing water hammer as a form of directed actuation. We show a novel concept of a Synthetic Neural Network, a type of an organic neuromorphic architecture modeled after Artificial Neural Network, which is used for a distributed cognition purposes for ACM. A simulation of the SNN is shown to accurately predict the directionality of water hammer propulsion.

Download Full-text

Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks

Frontiers in Neuroscience ◽

10.3389/fnins.2021.694549 ◽

2021 ◽

Vol 15 ◽

Author(s):

Corentin Delacour ◽

Aida Todri-Sanial

Keyword(s):

Neural Network ◽

Large Scale ◽

Hebbian Learning ◽

Hopfield Neural Network ◽

Analytical Framework ◽

Relaxation Oscillators ◽

Oscillatory Neural Network ◽

Network Functionality ◽

Fully Connected ◽

Neuromorphic Architecture

Oscillatory Neural Network (ONN) is an emerging neuromorphic architecture with oscillators representing neurons and information encoded in oscillator's phase relations. In an ONN, oscillators are coupled with electrical elements to define the network's weights and achieve massive parallel computation. As the weights preserve the network functionality, mapping weights to coupling elements plays a crucial role in ONN performance. In this work, we investigate relaxation oscillators based on VO2 material, and we propose a methodology to map Hebbian coefficients to ONN coupling resistances, allowing a large-scale ONN design. We develop an analytical framework to map weight coefficients into coupling resistor values to analyze ONN architecture performance. We report on an ONN with 60 fully-connected oscillators that perform pattern recognition as a Hopfield Neural Network.

Download Full-text

A Mixed-Signal Spiking Neuromorphic Architecture for Scalable Neural Network

2017 9th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) ◽

10.1109/ihmsc.2017.47 ◽

2017 ◽

Cited By ~ 2

Author(s):

Chong Luo ◽

Zhangzhong Ying ◽

Xiaolei Zhu ◽

Longlong Chen

Keyword(s):

Neural Network ◽

Mixed Signal ◽

Neuromorphic Architecture

Download Full-text

CREST project focused on neuromorphic devices and networks

Impact ◽

10.21820/23987073.2020.5.6 ◽

2020 ◽

Vol 2020 (5) ◽

pp. 6-9

Author(s):

Isao H Inoue

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Big Data ◽

Input Data ◽

Electronic Circuit ◽

Statistical Processing ◽

Low Power Consumption ◽

The Neural Network ◽

Artificial Neurons ◽

Neuromorphic Architecture

The artificial neural network is a type of electronic circuit modelled after the human brain. It contains thousands of artificial neurons and synapses that, in general, assemble to execute algorithms that can allow the neural network to incorporate a large amount of input data. One of the algorithms is known as deep learnig (DL), which is a kind of statistical processing to learn and infer several features of the big data while consuming tremendous energy. A team, led by Dr Isao H Inoue of the National Institute of Advanced Industrial Science and Technology (AIST), is working on a five-and-a-half-year CREST project until March 2025 to develop a novel neuromorphic architecture that can do the learning and inference without using such an algorithm, thus in low power consumption.

Download Full-text

Scalable Digital Neuromorphic Architecture for Large-Scale Biophysically Meaningful Neural Network With Multi-Compartment Neurons

IEEE Transactions on Neural Networks and Learning Systems ◽

10.1109/tnnls.2019.2899936 ◽

2020 ◽

Vol 31 (1) ◽

pp. 148-162 ◽

Cited By ~ 27

Author(s):

Shuangming Yang ◽

Bin Deng ◽

Jiang Wang ◽

Huiyan Li ◽

Meili Lu ◽

...

Keyword(s):

Neural Network ◽

Large Scale ◽

Neuromorphic Architecture

Download Full-text

НЕЙРОМОРФНЫЙ ПРОЦЕССОР «АЛТАЙ» ДЛЯ ЭНЕРГОЭФФЕКТИВНЫХ ВЫЧИСЛЕНИЙ

Nanoindustry Russia ◽

10.22184/1993-8578.2020.13.3s.531.538 ◽

2020 ◽

Vol 96 (3s) ◽

pp. 531-538

Author(s):

Н.В. Гришанов ◽

А.В. Зверев ◽

Д.Е. Ипатов ◽

В.М. Канглер ◽

М.Н. Катомин ◽

...

Keyword(s):

Neural Network ◽

Energy Consumption ◽

Image Recognition ◽

Network Inference ◽

Spiking Neural Network ◽

Test Image ◽

Neuromorphic Architecture

Предложена масштабируемая нейроморфная архитектура для исполнения импульсных нейронных сетей, разработан прототип СБИС с данной архитектурой. Проведены оценки энергопотребления проекта прототипа СБИС при распознавании тестовых изображений из наборов MNIST и CIFAR-10. The paper presents a scalable neuromorphic architecture for spiking neural network inference. A VLSI prototype based on this architecture has been developed. The energy consumption of the VLSI prototype project was estimated during a test image recognition from the MNIST and CIFAR-10 sets.

Download Full-text