Abstract
Mainstream standard LSTM architecture that is currently used in Tensorflow library does not use the original architecture. In fact, there are many different architectures of LSTM. One of the more widely used architectures of LSTM is Coupled Input and Forget Gate (CIFG). It is known more as Gated Recurrent Units (GRU). This chapter will introduce the existing architectures of LSTM. Further it will present memristive LSTM architecture implementation in analog hardware. The implementation realizes the standard version of LSTM architecture. Other architecture variations can be easily constructed by rearranging, adding, and deleting the existing analog circuit parts; and adding extra crossbar rows.
| Original language | English |
|---|---|
| Title of host publication | Modeling and Optimization in Science and Technologies |
| Publisher | Springer Verlag |
| Pages | 155-167 |
| Number of pages | 13 |
| DOIs | |
| Publication status | Published - Jan 1 2020 |
Publication series
| Name | Modeling and Optimization in Science and Technologies |
|---|---|
| Volume | 14 |
| ISSN (Print) | 2196-7326 |
| ISSN (Electronic) | 2196-7334 |
Fingerprint
ASJC Scopus subject areas
- Modelling and Simulation
- Medical Assisting and Transcription
- Applied Mathematics
Cite this
Memristive LSTM architectures. / Adam, Kazybek; Smagulova, Kamilya; James Pappachen, Alex.
Modeling and Optimization in Science and Technologies. Springer Verlag, 2020. p. 155-167 (Modeling and Optimization in Science and Technologies; Vol. 14).Research output: Chapter in Book/Report/Conference proceeding › Chapter
}
TY - CHAP
T1 - Memristive LSTM architectures
AU - Adam, Kazybek
AU - Smagulova, Kamilya
AU - James Pappachen, Alex
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Mainstream standard LSTM architecture that is currently used in Tensorflow library does not use the original architecture. In fact, there are many different architectures of LSTM. One of the more widely used architectures of LSTM is Coupled Input and Forget Gate (CIFG). It is known more as Gated Recurrent Units (GRU). This chapter will introduce the existing architectures of LSTM. Further it will present memristive LSTM architecture implementation in analog hardware. The implementation realizes the standard version of LSTM architecture. Other architecture variations can be easily constructed by rearranging, adding, and deleting the existing analog circuit parts; and adding extra crossbar rows.
AB - Mainstream standard LSTM architecture that is currently used in Tensorflow library does not use the original architecture. In fact, there are many different architectures of LSTM. One of the more widely used architectures of LSTM is Coupled Input and Forget Gate (CIFG). It is known more as Gated Recurrent Units (GRU). This chapter will introduce the existing architectures of LSTM. Further it will present memristive LSTM architecture implementation in analog hardware. The implementation realizes the standard version of LSTM architecture. Other architecture variations can be easily constructed by rearranging, adding, and deleting the existing analog circuit parts; and adding extra crossbar rows.
UR - http://www.scopus.com/inward/record.url?scp=85064745964&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064745964&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-14524-8_12
DO - 10.1007/978-3-030-14524-8_12
M3 - Chapter
AN - SCOPUS:85064745964
T3 - Modeling and Optimization in Science and Technologies
SP - 155
EP - 167
BT - Modeling and Optimization in Science and Technologies
PB - Springer Verlag
ER -