1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning
The rapid advancements in the field of autonomous systems have led to a significant demand for artificial‐intelligence‐of‐things (AIoT) edge‐compatible neuromorphic training accelerators with continual/online learning capability. These accelerators require a large network of synaptic elements with h...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-08-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202400912 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849230101093285888 |
|---|---|
| author | MD Yasir Bashir Pritish Sharma Shubham Sahay |
| author_facet | MD Yasir Bashir Pritish Sharma Shubham Sahay |
| author_sort | MD Yasir Bashir |
| collection | DOAJ |
| description | The rapid advancements in the field of autonomous systems have led to a significant demand for artificial‐intelligence‐of‐things (AIoT) edge‐compatible neuromorphic training accelerators with continual/online learning capability. These accelerators require a large network of synaptic elements with high degree of plasticity, high endurance, large integration density, and ultralow programing energy. Although emerging nonvolatile memories exhibit promising potential as synaptic devices, their widespread application in training accelerators is limited due to their low endurance and immature fabrication technology. In contrast, capacitor‐less 1 transistor‐dynamic random‐access memories (1T‐DRAMs) have recently emerged as lucrative alternative to the conventional (1T/1C) DRAMs owing to their high scalability and low footprint. Considering the high endurance, large integration density, and ultralow write energy of the 1T‐DRAMs, in this work, for the first time, their potential is explored as synaptic elements for online learning. The proposed 1T‐DRAM‐based synaptic element exhibits multi‐level capability (up to 6 bits), a large dynamic range (3.91 × 103), an ultralow energy, and an appreciable linearity for potentiation/depression. The 1T‐DRAM‐based synaptic element also exhibits a paired pulse facilitation with an exponential decay similar to the biological synapses. Furthermore, a multilayer perceptron utilizing the proposed 1T‐DRAM synapses achieves an accuracy of 87.10% on MNIST dataset. |
| format | Article |
| id | doaj-art-9fa403d4e92e4d15a3fb410827358952 |
| institution | Kabale University |
| issn | 2640-4567 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj-art-9fa403d4e92e4d15a3fb4108273589522025-08-21T11:05:47ZengWileyAdvanced Intelligent Systems2640-45672025-08-0178n/an/a10.1002/aisy.2024009121 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online LearningMD Yasir Bashir0Pritish Sharma1Shubham Sahay2Department of Electrical Engineering Indian Institute of Technology (IIT) Kanpur Kalyanpur Kanpur 208016 IndiaDepartment of Electrical Engineering Indian Institute of Technology (IIT) Kanpur Kalyanpur Kanpur 208016 IndiaDepartment of Electrical Engineering Indian Institute of Technology (IIT) Kanpur Kalyanpur Kanpur 208016 IndiaThe rapid advancements in the field of autonomous systems have led to a significant demand for artificial‐intelligence‐of‐things (AIoT) edge‐compatible neuromorphic training accelerators with continual/online learning capability. These accelerators require a large network of synaptic elements with high degree of plasticity, high endurance, large integration density, and ultralow programing energy. Although emerging nonvolatile memories exhibit promising potential as synaptic devices, their widespread application in training accelerators is limited due to their low endurance and immature fabrication technology. In contrast, capacitor‐less 1 transistor‐dynamic random‐access memories (1T‐DRAMs) have recently emerged as lucrative alternative to the conventional (1T/1C) DRAMs owing to their high scalability and low footprint. Considering the high endurance, large integration density, and ultralow write energy of the 1T‐DRAMs, in this work, for the first time, their potential is explored as synaptic elements for online learning. The proposed 1T‐DRAM‐based synaptic element exhibits multi‐level capability (up to 6 bits), a large dynamic range (3.91 × 103), an ultralow energy, and an appreciable linearity for potentiation/depression. The 1T‐DRAM‐based synaptic element also exhibits a paired pulse facilitation with an exponential decay similar to the biological synapses. Furthermore, a multilayer perceptron utilizing the proposed 1T‐DRAM synapses achieves an accuracy of 87.10% on MNIST dataset.https://doi.org/10.1002/aisy.2024009121 transistor(1 T)‐dynamic random access memories (1T‐DRAMs)gate‐induced drain leakages (GIDLs)lateral band‐to‐band‐tunneling (L‐BTBTs)nanowire FETs |
| spellingShingle | MD Yasir Bashir Pritish Sharma Shubham Sahay 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning Advanced Intelligent Systems 1 transistor(1 T)‐dynamic random access memories (1T‐DRAMs) gate‐induced drain leakages (GIDLs) lateral band‐to‐band‐tunneling (L‐BTBTs) nanowire FETs |
| title | 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning |
| title_full | 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning |
| title_fullStr | 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning |
| title_full_unstemmed | 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning |
| title_short | 1 Transistor‐Dynamic Random Access Memory as Synaptic Element for Online Learning |
| title_sort | 1 transistor dynamic random access memory as synaptic element for online learning |
| topic | 1 transistor(1 T)‐dynamic random access memories (1T‐DRAMs) gate‐induced drain leakages (GIDLs) lateral band‐to‐band‐tunneling (L‐BTBTs) nanowire FETs |
| url | https://doi.org/10.1002/aisy.202400912 |
| work_keys_str_mv | AT mdyasirbashir 1transistordynamicrandomaccessmemoryassynapticelementforonlinelearning AT pritishsharma 1transistordynamicrandomaccessmemoryassynapticelementforonlinelearning AT shubhamsahay 1transistordynamicrandomaccessmemoryassynapticelementforonlinelearning |