Liquid State Machine With Dendritically Enhanced Readout for Low-Power, Neuromorphic VLSI Implementations

被引:38
|
作者
Roy, Subhrajit [1 ]
Banerjee, Amitava [1 ]
Basu, Arindam [1 ]
机构
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
关键词
Binary synapse; liquid state machine; neuromorphic engineering; nonlinear dendrite; readout; supervised learning; DENDRITES; DYNAMICS;
D O I
10.1109/TBCAS.2014.2362969
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In this paper, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing. Compared to the parallel perceptron architecture trained by the p-delta algorithm, which is the state of the art in terms of performance of readout stages, our readout architecture and learning algorithm can attain better performance with significantly less synaptic resources making it attractive for VLSI implementation. Inspired by the nonlinear properties of dendrites in biological neurons, our readout stage incorporates neurons having multiple dendrites with a lumped nonlinearity (two compartment model). The number of synaptic connections on each branch is significantly lower than the total number of connections from the liquid neurons and the learning algorithm tries to find the best ` combination' of input connections on each branch to reduce the error. Hence, the learning involves network rewiring (NRW) of the readout network similar to structural plasticity observed in its biological counterparts. We show that compared to a single perceptron using analog weights, this architecture for the readout can attain, even by using the same number of binary valued synapses, up to 3.3 times less error for a two-class spike train classification problem and 2.4 times less error for an input rate approximation task. Even with 60 times larger synapses, a group of 60 parallel perceptrons cannot attain the performance of the proposed dendritically enhanced readout. An additional advantage of this method for hardware implementations is that the ` choice' of connectivity can be easily implemented exploiting address event representation (AER) protocols commonly used in current neuromorphic systems where the connection matrix is stored in memory. Also, due to the use of binary synapses, our proposed method is more robust against statistical variations.
引用
收藏
页码:681 / 695
页数:15
相关论文
共 50 条
  • [31] A Low-Power ECG Readout Circuit Integrated with Machine Learning Based ECG Heartbeat Classifier
    Kota, Deepa
    Mahbub, Ifana
    2021 IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2021, : 639 - 643
  • [32] Low-Power Amplifier for Readout Interface of Semiconductor Scintillator
    Yun, Xiao
    Stanacevic, Milutin
    Luryi, Serge
    IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2011, 58 (04) : 2129 - 2136
  • [33] Low-power readout circuit for quanta image sensors
    Masoodian, S.
    Odame, K.
    Fossum, E. R.
    ELECTRONICS LETTERS, 2014, 50 (08) : 589 - 590
  • [34] CREATING LOW-POWER BIPOLAR ECL AT VLSI DENSITIES
    WILSON, G
    VLSI SYSTEMS DESIGN, 1986, 7 (05): : 84 - 86
  • [35] A COMPACT LOW-POWER VLSI TRANSCEIVER FOR WIRELESS COMMUNICATION
    BANG, SH
    CHOI, J
    SHEU, BJ
    CHANG, RC
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1995, 42 (11): : 933 - 945
  • [36] A low-power readout circuit design for capacitive microsensors
    Aezinia, Fatemeh
    Bahreyni, Behraad
    2015 IEEE SENSORS, 2015, : 839 - 842
  • [37] A novel low-power readout structure for TDI ROIC
    Lu, WG
    Gao, J
    Chen, ZJ
    Liu, J
    Cui, WT
    Tang, J
    Ji, LJ
    2003 5TH INTERNATIONAL CONFERENCE ON ASIC, VOLS 1 AND 2, PROCEEDINGS, 2003, : 591 - 594
  • [38] Low-power VLSI decoder architectures for LDPC codes
    Mansour, MM
    Shanbhag, NR
    ISLPED'02: PROCEEDINGS OF THE 2002 INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN, 2002, : 284 - 289
  • [39] Low-power Analog VLSI Implementation of Wavelet Transform
    ZHANG Jiang-hong(College of Electrical and Information Engineering
    Semiconductor Photonics and Technology, 2009, 15 (02) : 86 - 89
  • [40] CMOS VLSI implementation of a low-power logarithmic converter
    Abed, KH
    Siferd, RE
    IEEE TRANSACTIONS ON COMPUTERS, 2003, 52 (11) : 1421 - 1433