Evolving Neuromorphic Systems on the Ethereum Smart Contract Platform

【Author】 Wu, Hongchi; Fang, Binhao; Xiang, Cheng; Cohen, Gregory; Van Schaik, Andre; Ramesh, Bharath

【Source】2022 IEEE 1ST GLOBAL EMERGING TECHNOLOGY BLOCKCHAIN FORUM: BLOCKCHAIN & BEYOND, IGETBLOCKCHAIN

【影响因子】

【Abstract】Neuromorphic intelligent systems are motivated by the observation that biological organisms - from algae to primates - excel in swiftly sensing their environment, reacting promptly to its perils and opportunities. Furthermore, biological organisms function more resiliently than our most advanced machines, with a fraction of their power requirements. Taking inspiration from how primates and humans have successfully evolved higher cognitive intelligence within social constructs, this paper proposes neuromorphic systems to be built and governed on a public distributed ledger platform. However, following in the footsteps of generic AI research, neuromorphic benchmarks and algorithms are developed in isolation. Furthermore, as a relatively niche research field, there is limited access to the actual neuromorphic sensors and large publicly available curated data, exacerbating the slow research progress. Nonetheless, centralized neuromorphic datasets and algorithms pose a threat to secure closed-loop behavior and learning outcomes, both commonly modulated in biological organisms via social interactions. This paper makes the case for early adoption of distributed ledger technology by neuromorphic systems and benchmarks to avoid the pitfalls endured by AI research - showcasing competing event-based gesture recognition systems on the Ethereum smart contract platform. This shift towards real-world and dynamic systems on a distributed ledger platform will improve collaboration among neuromorphic researchers while enabling healthy competition via incentives. Smart contract protocols allow model behavior monitoring, setting new learning tasks and increase in baseline performance, and naturally provides a governance framework for evolving neuromorphic systems. The code is publicly made available at: https://gist.github.com/BruceFang123.

【Keywords】neuromorphic engineering; blockchain; smart contract; dynamic vision sensor; gesture recognition; event-based processing

【发表时间】2022

【收录时间】2023-06-25

【文献类型】理论模型

【主题类别】

区块链应用-实体经济-生物领域