Performance of Crossbar based Long Short Term Memory with Aging Memristors

The Long Short Term Memory (LSTM) neural networks find a wide range of applications in time series prediction problems. The long-term accuracy and reliability of LSTM memristor crossbar array are subjected to the memristor device’s endurance and failures. Memristor aging and its impact on such LSTM’s performance is an open problem. This paper analyzes the effects of different types of aging typically exhibited in memristor devices on the crossbar performance. The performance results are analyzed on two datasets, (1) SMS Spam and (2) IMDB movie review. Our analysis indicated that the different aging type shows different performance deterioration levels in the crossbar based LSTM system. Here, the aging analysis for oxide-based memristor implementation are primarily considered when used in CMOS-Memristor hybrid crossbars.

[1]  Hyunsang Hwang,et al.  Perspective: A review on memristive hardware for neuromorphic computation , 2018, Journal of Applied Physics.

[2]  Alex Pappachen James,et al.  A survey on LSTM memristive neural network architectures and applications , 2019, The European Physical Journal Special Topics.

[3]  Haider Abbas,et al.  Towards engineering in memristors for emerging memory and neuromorphic computing: A review , 2021, Journal of Semiconductors.

[4]  Zhigang Zeng,et al.  Memristor-based LSTM network with in situ training and its applications , 2020, Neural Networks.

[5]  H.-S. Philip Wong,et al.  In-memory computing with resistive switching devices , 2018, Nature Electronics.

[6]  Alex Pappachen James,et al.  A memristor-based long short term memory circuit , 2018 .

[7]  Zhisong Xiao,et al.  Neuromorphic Computing with Memristor Crossbar , 2018 .

[8]  Abdullah M. Zyarah,et al.  Neuromemristive Multi-Layer Random Projection Network with On-Device Learning , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[9]  Antonio Rubio,et al.  Reliability challenges in design of memristive memories , 2014, 2014 5th European Workshop on CMOS Variability (VARI).

[10]  Leon O. Chua,et al.  Analog Self-Timed Programming Circuits for Aging Memristors , 2021, IEEE Transactions on Circuits and Systems II: Express Briefs.

[11]  E. Eleftheriou,et al.  Memory devices and applications for in-memory computing , 2020, Nature Nanotechnology.

[12]  Ulf Schlichtmann,et al.  Aging-aware Lifetime Enhancement for Memristor-based Neuromorphic Computing , 2019, 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[13]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[14]  Akebo Yamakami,et al.  Contributions to the study of SMS spam filtering: new collection and results , 2011, DocEng '11.

[15]  Indranil Sengupta,et al.  Analyzing Fault Tolerance Behaviour in Memristor-based Crossbar for Neuromorphic Applications , 2020, 2020 IEEE International Test Conference India.