Neuromorphic Neural Engineering Framework-Inspired Online Continuous Learning with Analog Circuitry

被引:9
作者
Hazan, Avi [1 ]
Ezra Tsur, Elishai [1 ]
机构
[1] Open Univ Israel, Dept Math & Comp Sci, Neurobiomorph Engn Lab, IL-4353701 Raanana, Israel
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 09期
关键词
OZ spiking neurons; NEF; Nengo; REACH; prescribed error sensitivity; neuromorphic engineering; neuromorphic computing; machine learning; online learning; real-time learning; adaptive robotics; neurorobotics; MuJoCo; NETWORKS; NEURONS; SYSTEM;
D O I
10.3390/app12094528
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Neuromorphic hardware designs realize neural principles in electronics to provide high-performing, energy-efficient frameworks for machine learning. Here, we propose a neuromorphic analog design for continuous real-time learning. Our hardware design realizes the underlying principles of the neural engineering framework (NEF). NEF brings forth a theoretical framework for the representation and transformation of mathematical constructs with spiking neurons, thus providing efficient means for neuromorphic machine learning and the design of intricate dynamical systems. Our analog circuit design implements the neuromorphic prescribed error sensitivity (PES) learning rule with OZ neurons. OZ is an analog implementation of a spiking neuron, which was shown to have complete correspondence with NEF across firing rates, encoding vectors, and intercepts. We demonstrate PES-based neuromorphic representation of mathematical constructs with varying neuron configurations, the transformation of mathematical constructs, and the construction of a dynamical system with the design of an inducible leaky oscillator. We further designed a circuit emulator, allowing the evaluation of our electrical designs on a large scale. We used the circuit emulator in conjunction with a robot simulator to demonstrate adaptive learning-based control of a robotic arm with six degrees of freedom.
引用
收藏
页数:16
相关论文
共 33 条
  • [1] [Anonymous], 1973, SPICE SIMULATION PRO
  • [2] Applied Brain Research Inc, PES LEARN
  • [3] Nengo: a Python']Python tool for building large-scale functional brain models
    Bekolay, Trevor
    Bergstra, James
    Hunsberger, Eric
    DeWolf, Travis
    Stewart, Terrence C.
    Rasmussen, Daniel
    Choo, Xuan
    Voelker, Aaron Russell
    Eliasmith, Chris
    [J]. FRONTIERS IN NEUROINFORMATICS, 2014, 7
  • [4] Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations
    Benjamin, Ben Varkey
    Gao, Peiran
    McQuinn, Emmett
    Choudhary, Swadesh
    Chandrasekaran, Anand R.
    Bussat, Jean-Marie
    Alvarez-Icaza, Rodrigo
    Arthur, John V.
    Merolla, Paul A.
    Boahen, Kwabena
    [J]. PROCEEDINGS OF THE IEEE, 2014, 102 (05) : 699 - 716
  • [5] A Neuromorph's Prospectus
    Boahen, Kwabena
    [J]. COMPUTING IN SCIENCE & ENGINEERING, 2017, 19 (02) : 14 - 15
  • [6] Loihi: A Neuromorphic Manycore Processor with On-Chip Learning
    Davies, Mike
    Srinivasa, Narayan
    Lin, Tsung-Han
    Chinya, Gautham
    Cao, Yongqiang
    Choday, Sri Harsha
    Dimou, Georgios
    Joshi, Prasad
    Imam, Nabil
    Jain, Shweta
    Liao, Yuyun
    Lin, Chit-Kwan
    Lines, Andrew
    Liu, Ruokun
    Mathaikutty, Deepak
    Mccoy, Steve
    Paul, Arnab
    Tse, Jonathan
    Venkataramanan, Guruguhanathan
    Weng, Yi-Hsin
    Wild, Andreas
    Yang, Yoonseok
    Wang, Hong
    [J]. IEEE MICRO, 2018, 38 (01) : 82 - 99
  • [7] TrueNorth: Accelerating From Zero to 64 Million Neurons in 10 Years
    DeBole, Michael V.
    Taba, Brian
    Amir, Arnon
    Akopyan, Filipp
    Andreopoulos, Alexander
    Risk, William P.
    Kusnitz, Jeff
    Otero, Carlos Ortega
    Nayak, Tapan K.
    Appuswamy, Rathinakumar
    Carlson, Peter J.
    Cassidy, Andrew S.
    Datta, Pallab
    Esser, Steven K.
    Garreau, Guillaume J.
    Holland, Kevin L.
    Lekuch, Scott
    Mastro, Michael
    McKinstry, Jeff
    di Nolfo, Carmelo
    Paulovicks, Brent
    Sawada, Jun
    Schleupen, Kai
    Shaw, Benjamin G.
    Klamo, Jennifer L.
    Flickner, Myron D.
    Arthur, John V.
    Modha, Dharmendra S.
    [J]. COMPUTER, 2019, 52 (05) : 20 - 29
  • [8] Devices A, 2008, LTSPICE SIMULATOR
  • [9] A spiking neural model of adaptive arm control
    DeWolf, Travis
    Stewart, Terrence C.
    Slotine, Jean-Jacques
    Eliasmith, Chris
    [J]. PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2016, 283 (1843)
  • [10] Eliasmith C., 2004, Neural Engineering: Computational, Representation, and Dynamics in Neurobiological Systems