A system design approach to neuromorphic classifiers

Analog signal processing;Machine learning;Bio-inspired

Ramakrishnan, Shubha ; Hasler, Jennifer Electrical and Computer Engineering Anderson, David Butera, Robert Culurciello, Eugenio Lim, Sung-Kyu ; Hasler, Jennifer

University:Georgia Institute of Technology

Department:Electrical and Computer Engineering

关键词: Analog signal processing;    Machine learning;    Bio-inspired;   

Others  :  https://smartech.gatech.edu/bitstream/1853/51718/1/ramakrishnan_shubha_201305_phd.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

This work considers alternative strategies to mainstream digital approaches to signal processing - namely analog and neuromorphic solutions, for increased computing efficiency. In the context of a speech recognizer application, we use low-power analog approaches for the signal conditioning and basic auditory feature extraction, while using a neuromorphic IC for building a dendritic classifier that can be used as a low-power word spotter. In doing so, this work also aspires to posit the significance of dendrites in neural computation.