PROJECT TITLE :

Energy Efficient Approximate Arithmetic for Error Resilient Neuromorphic Computing

ABSTRACT:

This temporary proposes a unique style theme for approximate adders and comparators to considerably cut back energy consumption while maintaining a very low error rate. The significantly improved error rate and crucial path delay stem from the used carry prediction technique that leverages the information from less significant input bits in a very parallel manner. The proposed styles have been adopted in an exceedingly VLSI-based mostly neuromorphic character recognition chip with unsupervised learning implemented on chip. The approximation errors of the proposed arithmetic units have been shown to have negligible impact on the training process while archiving smart energy efficiency.