Robust Learning and Recognition of Visual Patterns in Neuromorphic Electronic Agents
| Autor: | Giacomo Indiveri, Carsten Nielsen, Ning Qiao, Dongchen Liang, Yulia Sandamirskaya, Raphaela Kreiser |
|---|---|
| Přispěvatelé: | University of Zurich |
| Rok vydání: | 2019 |
| Předmět: |
Spiking neural network
0209 industrial biotechnology Quantitative Biology::Neurons and Cognition Computer science Neural substrate 1708 Hardware and Architecture 2208 Electrical and Electronic Engineering Inference 1702 Artificial Intelligence 02 engineering and technology Computer Science::Hardware Architecture Computer Science::Emerging Technologies 020901 industrial engineering & automation Neuromorphic engineering Computer engineering Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering 570 Life sciences biology Unsupervised learning 020201 artificial intelligence & image processing 10194 Institute of Neuroinformatics |
| Zdroj: | AICAS |
| Popis: | Mixed-signal analog/digital neuromorphic circuits are characterized by ultra-low power consumption, real-time processing abilities, and low-latency response times. These features make them promising for robotic applications that require fast and power-efficient computing. However, the unavoidable variance inherently existing in the analog circuits makes it challenging to develop neural processing architectures able to perform complex computations robustly. In this paper, we present a spiking neural network architecture with spike-based learning that enables robust learning and recognition of visual patterns in noisy silicon neural substrate and noisy environments. The architecture is used to perform pattern recognition and inference after a training phase with computers and neuromorphic hardware in the loop. We validate the proposed system in a closed-loop hardware setup composed of neuromorphic vision sensors and processors, and we present experimental results that quantify its real-time and robust perception and action behavior. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|