Computational Primitives in Neuromorphic VLSI Systems

Journal Title: International Journal of Engineering and Science Invention - Year 2017, Vol 6, Issue 11

Abstract

Understanding how to reproduce robust and reli-able decision making behavior in neuromorphic systems can be useful for developing information processing architectures in subthreshold analog circuits as well as future emerging nano-technologies, that comprise inhomogeneous and unreliable components. To this end, we explore the computational properties of a recurrent neural network, implemented in a custom mixed signal analog/digital neuromorphic chip, for realizing perceptual decision-making, bi-stable perception, and working memory. The chip comprises conductance-based integrate-and-fire neurons and configurable synapses with realistic dynamics. These circuits are configured to implement a recurrent neural network, composed of excitatory and inhibitory pools of silicon neurons coupled with local excitation and global inhibition. We show how the interplay between excitation and inhibition produces competitive winnertake-all dynamics, which is a feature of decision-making and persistent activity models, and demonstrate that the system generates reliable dynamics capable of reproducing both neuro-physiological data and psychophysical performances in coding and collective distributed computation.

Authors and Affiliations

R N S Kalpana

Keywords

Related Articles

Image Encryption using chaotic logistic maps with larger key

Chaos-Based encryption technology has been studied for decades and it has become an important branch of cryptography because of its interesting features such as high security, speed, and dynamic in nature. The encryption...

Syntheses and Characterization of 1-D Titanium Glycolate microstructures: Effect of Dilution and Addition type on the Morphology of microstructures

Titanium glycolate is synthesized by the reaction of titanium butoxide with monoethylene glycol. This is a quick and convenient method for the preparation of titanium glycolate; the glycol acts as both reactant as well a...

Each node acts as a base station and is responsible for dynamically discovering other nodes it can directly communicate with In MANET

In this paper, we utilize the Wireless networks, nodes can communicate through base stations. In this scenario, the communication process takes more time to complete. To reduce this delay time, a Mobile Ad hoc Network is...

Some Observations on Community Detection Algorithms in Social Networks

This paper focuses on community detection algorithms in social networks. We have given a brief background about graph, social networks and community detection. The popular algorithms used for community detection are cate...

Synthesis And Characterization Of Schiff Base Metal Complexes Of Zr(IV) And Th(IV) Using (DFMPM) And L-Alanine

Schiff base nano complexes of Zirconium(IV) and Thorium(IV) of general composition ML2 have been synthesized using DFMPM and L-alanine. The complexes were prepared by standared methods.The melting point, elemental analys...

Download PDF file
  • EP ID EP403912
  • DOI -
  • Views 61
  • Downloads 0

How To Cite

R N S Kalpana (2017). Computational Primitives in Neuromorphic VLSI Systems. International Journal of Engineering and Science Invention, 6(11), 32-38. https://europub.co.uk/articles/-A-403912