Abstract :
In the last decade, progress has been made in the construction of simple neuromorphic cognitive systems. These types of circuits are described in the paper, and they are compared to existing solutions. The limitations of such circuits are described, as well as design techniques for constructing larger brain-like systems. The technological building blocks are based on dynamic synapse circuits, hardware models of spiking neurons, and spike-based plasticity circuits, which are integrated into multichip spiking recurrent and winner-take-all neural networks, which can serve as models for pattern recognition, working memory, decision making, and state-dependent brain computing.
Keywords :
CMOS analogue integrated circuits; VLSI; cognitive systems; decision making; neural chips; neurophysiology; pattern recognition; VLSI circuits; autonomous cognitive systems; brain-like systems; decision making; dynamic synapse circuits; multichip spiking recurrent; neuromorphic electronic circuits; pattern recognition; spike-based plasticity circuits; spiking neurons; state-dependent brain computing; very large scale integration; winner-take-all neural networks; working memory; Analog circuits; Brain modeling; Cognitive science; Computational modeling; Computer architecture; Integrated circuit modeling; Neural networks; Neuromorphics; Real-time systems; Special issues and sections; Very large scale integration;
