A Highly Robust Binary Neural Network Inference Accelerator Based on Binary Memristors
| Autor: | Yiyang Zhao, Yuan Rong, Xianyang Jiang, Yongjia Wang, Ruibo Wang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
non-ideal factors
binary neural network (BNN) Hardware_MEMORYSTRUCTURES Artificial neural network TK7800-8360 Computer Networks and Communications Computer science Binary number Verilog-AMS Memristor Topology law.invention Neuromorphic engineering Hardware and Architecture Control and Systems Engineering law Signal Processing Voltage source Electrical and Electronic Engineering Circuit complexity Electronics memristor MNIST database |
| Zdroj: | Electronics, Vol 10, Iss 2600, p 2600 (2021) Electronics Volume 10 Issue 21 |
| ISSN: | 2079-9292 |
| Popis: | Since memristor was found, it has shown great application potential in neuromorphic computing. Currently, most neural networks based on memristors deploy the special analog characteristics of memristor. However, owing to the limitation of manufacturing process, non-ideal characteristics such as non-linearity, asymmetry, and inconsistent device periodicity appear frequently and definitely, therefore, it is a challenge to employ memristor in a massive way. On the contrary, a binary neural network (BNN) requires its weights to be either +1 or −1, which can be mapped by digital memristors with high technical maturity. Upon this, a highly robust BNN inference accelerator with binary sigmoid activation function is proposed. In the accelerator, the inputs of each network layer are either +1 or 0, which can facilitate feature encoding and reduce the peripheral circuit complexity of memristor hardware. The proposed two-column reference memristor structure together with current controlled voltage source (CCVS) circuit not only solves the problem of mapping positive and negative weights on memristor array, but also eliminates the sneak current effect under the minimum conductance status. Being compared to the traditional differential pair structure of BNN, the proposed two-column reference scheme can reduce both the number of memristors and the latency to refresh the memristor array by nearly 50%. The influence of non-ideal factors of memristor array such as memristor array yield, memristor conductance fluctuation, and reading noise on the accuracy of BNN is investigated in detail based on a newly memristor circuit model with non-ideal characteristics. The experimental results demonstrate that when the array yield α ≥ 5%, or the reading noise σ ≤ 0.25, a recognition accuracy greater than 97% on the MNIST data set is achieved. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|