Abstract
Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm2, and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities.
Highlights
Recent advances in neural network modeling and theory, combined with advances in technology and computing power, are producing impressive results in a wide range of application domains
Attractor Networks In this experiment we explored the collective dynamics of multiple populations of spiking silicon neurons that emulate the biophysics of cortical neurons organized in attractor networks (Amit, 1992)
When the attractor networks are being driven by external stimuli their activity reaches a mean rate of approximately 50 Hz and, after the removal of these stimuli, the pools of neurons relax to a sustained state of activity of about 15 Hz, indicating that the neurons settled into their attractor states
Summary
Recent advances in neural network modeling and theory, combined with advances in technology and computing power, are producing impressive results in a wide range of application domains. A learning neuromorphic processor systems are typically composed of custom Very Large Scale Integration (VLSI) chips that either contain digital processing cores with dedicated memory structures and communication schemes optimized for spiking neural networks architectures (Wang et al, 2013; Furber et al, 2014; Neil and Liu, 2014), or full-custom digital circuit solutions that implement large arrays of spiking neurons with programmable synaptic connections (Merolla et al, 2014). While these devices and systems have high potential for solving machine learning tasks and applied research problems, they do not emulate directly the dynamics of real neural systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
