Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: neuromorphic computing

Sortuj według:

Ogranicz wyniki do:

The bioinspired traffic sign classifier

Przewlocka-Rus Dominika, Kryjak Tomasz

Bio-Algorithms and Med-Systems

2022

Vol. 18, no. 1

29--38

Objectives: In this paper the research on developing convolutional spiking neural networks for traffic signs classification is presented. Unlike classical ones, spiking networks reflect the behaviour of biological neurons much more closely, by taking into account the time dimension and event-based operation. Spiking networks running on dedicated neuromorphic platforms, such as Intel Loihi, can operate with greater energy efficiency, hence they are an interesting approach for embedded solutions. Methods: For convolutional spiking neural networks' design and simulation, Nengo and NengoDL libraries for Python language were used. Numerous experiments using the Leaky-Integrate-and-Fire (LIF) neuron model were conducted. The training results, with different augmentation methods and number of time steps for input image presentation were compared. Results: Finally, an accuracy of up to 97% on the test set was achieved, depending on the number of time steps the input was presented to the SNN. Conclusions: The proposed experiments show that using simple convolutional spiking neural network, one can achieve accuracy comparable to the classical network with the same architecture and trained on the same dataset. At the same time, running on dedicated neuromorphic hardware, such solution should be characterized by low latency and low energy consumption.

Memristor - old history and new development

Garczarczyk Z.

Prace Naukowe Politechniki Śląskiej. Elektryka

2009

z. 2

119-124

A brief survey of the properties of a memristor and memristive systems as well as the latest achievements in this field are presented in the paper. The memristor was postulated as a fourth missing circuit element in 1971. It was only a theoretical concept for many years. In May 2008 Hewlett-Packard Labs discovered that the memristor could be realized physically and find new applications to electronic systems.

W pracy dokonano krótkiego przeglądu własności memrystora i systemów memrystorowych oraz ostatnich osiągnięć w tej dziedzinie. Memrystor był postulowany jako czwarty brakujący element obwodu już w 1971 roku. Element ten przez wiele lat miał charakter wyłącznie teoretyczny. Wyniki badań uzyskane w 2008 roku w Hewlett-Packard Laboratory wskazująna możliwość jego fizycznej realizacji i wykorzystania w układach elektronicznych do nowych zastosowań.