TY - GEN
T1 - A low voltage discriminant circuit for pattern recognition exploiting the asymmetrical characteristics of tunnel FET
AU - Japa, Aditya
AU - Palagani, Yellappa
AU - Gonuguntla, Venkateswarlu
AU - Majumder, Manoj Kumar
AU - Sahoo, Subhendu K.
AU - Choi, Jun Rim
AU - Vaddi, Ramesh
N1 - Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - This paper exploits tunnel field-effect transistors (TFET) unique asymmetrical device characteristics, demonstrating discriminant circuits for pattern recognition useful in machine learning-based VLSI and IoT designs. In contrast to unidirectional current conduction in TFET, it exhibits significant p-i-n leakage current with increase in negative drain-to-source voltage. Due to this characteristics, TFET transmission gate exhibits distinct behavior. Exploiting this behavior, a ring oscillator (RO) is designed that can sense the changes in operating frequency with response to the pattern of control bits. Utilizing this RO, a discriminant circuit is demonstrated which is highly energy efficient with an ultra-low energy consumption of 34.5 pJ at supply voltage of 0.4 V and much suits the demands of emerging machine learning-based VLSI systems. The simplicity of discriminant circuit makes the architecture of pattern recognition engine simpler and reduces the energy overheads.
AB - This paper exploits tunnel field-effect transistors (TFET) unique asymmetrical device characteristics, demonstrating discriminant circuits for pattern recognition useful in machine learning-based VLSI and IoT designs. In contrast to unidirectional current conduction in TFET, it exhibits significant p-i-n leakage current with increase in negative drain-to-source voltage. Due to this characteristics, TFET transmission gate exhibits distinct behavior. Exploiting this behavior, a ring oscillator (RO) is designed that can sense the changes in operating frequency with response to the pattern of control bits. Utilizing this RO, a discriminant circuit is demonstrated which is highly energy efficient with an ultra-low energy consumption of 34.5 pJ at supply voltage of 0.4 V and much suits the demands of emerging machine learning-based VLSI systems. The simplicity of discriminant circuit makes the architecture of pattern recognition engine simpler and reduces the energy overheads.
KW - Machine learning-based circuits
KW - P-i-n leakage current
KW - Pattern recognition
KW - Tunnel field-effect transistor
UR - http://www.scopus.com/inward/record.url?scp=85109287548&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85109287548
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
BT - 2020 IEEE International Symposium on Circuits and Systems, ISCAS 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020
Y2 - 10 October 2020 through 21 October 2020
ER -
