Time-Domain Digital-to-Analog Converter for Spiking Neural Network Hardware

Analog Converter ◽

Exponential Equations ◽

Neural Network Hardware ◽

Digital To Analog ◽

Input Code ◽

Synaptic Responses

AbstractWe propose a new digital-to-analog converter (DAC) for realizing a synapse circuit in mixed-signal spiking neural networks. We refer to this circuit as a “time-domain DAC (TDAC)”. It produces weights for converting a digital input code into voltage using one current waveform. Therefore, the TDAC is more compact than a conventional DAC consisting of many current sources and resistors. Moreover, a TDAC with leak resistance reproduces biologically plausible synaptic responses expressed as alpha functions or dual exponential equations. We also present numerical analysis results for a TDAC and circuit simulation results for a circuit designed using the TSMC 40 nm CMOS process.

Compact, precise digital to analog converter arrays in a low cost, low precision short channel CMOS process

Proceedings of 1994 37th Midwest Symposium on Circuits and Systems ◽

10.1109/mwscas.1994.519020 ◽

2002 ◽

Cited By ~ 1

Author(s):

J.A. Tabler ◽

R. Poddar ◽

M. Brooke

Keyword(s):

Low Cost ◽

Cmos Process ◽

Short Channel ◽

Analog Converter ◽

2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE) ◽

Extreme wide-temperature range 8-bit digital to analog converter in bulk CMOS process

10.1109/ccece.2014.6901016 ◽

2014 ◽

Cited By ~ 3

Author(s):

Kevin S. Greig ◽

Vamsy P. Chodavarapu

Keyword(s):

Wide Temperature Range ◽

Cmos Process ◽

Temperature Range ◽

Analog Converter ◽

CMOS mixed-signal spiking neural network circuit using a time-domain digital-to-analog converter

2021 IEEE International Symposium on Circuits and Systems (ISCAS) ◽

10.1109/iscas51556.2021.9401230 ◽

2021 ◽

Author(s):

Seiji Uenohara ◽

Kazuyuki Aihara

Keyword(s):

Neural Network ◽

Time Domain ◽

Spiking Neural Network ◽

Mixed Signal ◽

Analog Converter ◽

A Low Power Op Amp for 3-Bit Digital to Analog Converter in 0.18 m CMOS Process

Research Journal of Applied Sciences Engineering and Technology ◽

10.19026/rjaset.5.4701 ◽

2013 ◽

Vol 5 (8) ◽

pp. 2592-2598

Author(s):

Noor A.B.A. Taib ◽

Md. Mamun ◽

Labonnah F. Rahman ◽

F.H. Hashim

Keyword(s):

Low Power ◽

Cmos Process ◽

Op Amp ◽

Analog Converter ◽

Compact, precise digital to analog converter arrays in a low cost, low precision short channel CMOS process

Proceedings of 1994 37th Midwest Symposium on Circuits and Systems ◽

10.1109/mwscas.1994.1532038 ◽

1994 ◽

Author(s):

J.A. Tabler ◽

R. Poddar ◽

M. Brooke

Keyword(s):

Low Cost ◽

Cmos Process ◽

Short Channel ◽

Analog Converter ◽

Increasing the information capacity of a fiber-optic multi-sensor converter of binary mechanical signals into electrical signals

Izmeritel`naya Tekhnika ◽

10.32446/0368-1025it.2020-9-15-23 ◽

2020 ◽

pp. 15-23

Author(s):

V. M. Grechishnikov ◽

E. G. Komarov

Keyword(s):

Fiber Optic ◽

Information Capacity ◽

Parallel Structure ◽

Optical Scheme ◽

Electrical Signals ◽

Mechanical Signals ◽

Analog Converter ◽

Output Code ◽

The design and operation principle of a multi-sensor Converter of binary mechanical signals into electrical signals based on a partitioned fiber-optic digital-to-analog Converter with a parallel structure is considered. The digital-to-analog Converter is made from a set of simple and technological (three to five digit) fiber-optic digital-to-analog sections. The advantages of the optical scheme of the proposed. Converter in terms of metrological and energy characteristics in comparison with single multi-bit converters are justified. It is shown that by increasing the number of digital-analog sections, it is possible to repeatedly increase the information capacity of a multi-sensor Converter without tightening the requirements for its manufacturing technology and element base. A mathematical model of the proposed Converter is developed that reflects the features of its operation in the mode of sequential time conversion of the input code vectors of individual fiber-optic sections into electrical analogues and the formation of the resulting output code vector.

Development of a Non-Volatile Programmable Digital to Analog Converter Subsystem for PCM (Pulse-Code Modification) Telemetry Systems.

10.21236/ada137878 ◽

1983 ◽

Author(s):

W. B. Harkey ◽

V. R. Parkerson

Keyword(s):

Analog Converter ◽

Digital To Analog ◽

Code Modification

First demonstration of a semiconductor-integrated optical digital-to-analog converter

31st European Conference on Optical Communications (ECOC 2005) ◽

10.1049/cp:20050464 ◽

2005 ◽

Author(s):

H. Uenohara

Keyword(s):

Integrated Optical ◽

Analog Converter ◽

10-Gsymbol/s IM-based quantum noise encryption system modulated by a dual digital‐to‐analog converter

Optical and Quantum Electronics ◽

10.1007/s11082-020-02699-6 ◽

2021 ◽

Vol 53 (1) ◽

Author(s):

Shuai Shi ◽

Ning Xiao

Keyword(s):

Quantum Noise ◽

Analog Converter ◽

Coded Control of a Sectional Electroelastic Engine for Nanomechatronics Systems

Applied System Innovation ◽

10.3390/asi4030047 ◽

2021 ◽

Vol 4 (3) ◽

pp. 47

Author(s):

Sergey M. Afonin

Keyword(s):

Transfer Function ◽

Mechanical Load ◽

Inertial Load ◽

Transient Characteristics ◽

Analog Converter ◽

This work determines the coded control of a sectional electroelastic engine at the elastic–inertial load for nanomechatronics systems. The expressions of the mechanical and adjustment characteristics of a sectional electroelastic engine are obtained using the equations of the electroelasticity and the mechanical load. A sectional electroelastic engine is applied for coded control of nanodisplacement as a digital-to-analog converter. The transfer function and the transient characteristics of a sectional electroelastic engine at elastic–inertial load are received for nanomechatronics systems.