ridm@nrct.go.th   ระบบคลังข้อมูลงานวิจัยไทย   รายการโปรดที่คุณเลือกไว้

Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines

หน่วยงาน Nanyang Technological University, Singapore

รายละเอียด

ชื่อเรื่อง : Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines
นักวิจัย : Roy, Subhrajit , Basu, Arindam , Hussain, Shaista
คำค้น : DRNTU::Engineering::Electrical and electronic engineering
หน่วยงาน : Nanyang Technological University, Singapore
ผู้ร่วมงาน : -
ปีพิมพ์ : 2556
อ้างอิง : Roy, S., Basu, A. & Hussain, S. 2013. Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines. IEEE Biomedical Circuits and Systems Conference (BioCAS) 2013, 302 - 305. , http://hdl.handle.net/10220/19535 , http://dx.doi.org/10.1109/BioCAS.2013.6679699 , 175591
ที่มา : -
ความเชี่ยวชาญ : -
ความสัมพันธ์ : -
ขอบเขตของเนื้อหา : -
บทคัดย่อ/คำอธิบาย :

In this article, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM) that is suitable for on-sensor computing in resource constrained applications. Compared to the state of the art parallel perceptron readout (PPR), 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 even while using binary synapses, our method can achieve 2.4 - 3.3 times less error compared to PPR using same number of high resolution synapses. Conversely, PPR requires 40-60 times more synapses to attain error levels comparable to our method.

บรรณานุกรม :
Roy, Subhrajit , Basu, Arindam , Hussain, Shaista . (2556). Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines.
    กรุงเทพมหานคร : Nanyang Technological University, Singapore.
Roy, Subhrajit , Basu, Arindam , Hussain, Shaista . 2556. "Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines".
    กรุงเทพมหานคร : Nanyang Technological University, Singapore.
Roy, Subhrajit , Basu, Arindam , Hussain, Shaista . "Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines."
    กรุงเทพมหานคร : Nanyang Technological University, Singapore, 2556. Print.
Roy, Subhrajit , Basu, Arindam , Hussain, Shaista . Hardware efficient, neuromorphic dendritically enhanced readout for liquid state machines. กรุงเทพมหานคร : Nanyang Technological University, Singapore; 2556.