RT Journal Article
T1 Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
A1 Makarov Slizneva, Valeriy
A1 Lobov, Sergey A.
A1 Shchanikov, Sergey
A1 Mikhaylov, Alexey
A1 Kazantsev, Viktor B.
AB The design of modern convolutional artificial neural networks (ANNs) composed of formal neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy, where receptive fields become increasingly more complex and coding sparse. Nowadays, ANNs outperform humans in controlled pattern recognition tasks yet remain far behind in cognition. In part, it happens due to limited knowledge about the higher echelons of the brain hierarchy, where neurons actively generate predictions about what will happen next, i.e., the information processing jumps from reflex to reflection. In this study, we forecast that spiking neural networks (SNNs) can achieve the next qualitative leap. Reflective SNNs may take advantage of their intrinsic dynamics and mimic complex, not reflex-based, brain actions. They also enable a significant reduction in energy consumption. However, the training of SNNs is a challenging problem, strongly limiting their deployment. We then briefly overview new insights provided by the concept of a high-dimensional brain, which has been put forward to explain the potential power of single neurons in higher brain stations and deep SNN layers. Finally, we discuss the prospect of implementing neural networks in memristive systems. Such systems can densely pack on a chip 2D or 3D arrays of plastic synaptic contacts directly processing analog information. Thus, memristive devices are a good candidate for implementing in-memory and in-sensor computing. Then, memristive SNNs can diverge from the development of ANNs and build their niche, cognitive, or reflective computations.
PB Frontiers Media
SN 1662-5188
YR 2022
FD 2022-06-16
LK https://hdl.handle.net/20.500.14352/71954
UL https://hdl.handle.net/20.500.14352/71954
LA eng
NO Russian Science Foundation
NO Russian Foundation for Basic Research
NO Ministry of Education and Science of Russia
NO Santander-UCM
DS Docta Complutense
RD 12 abr 2025