.png){kind=icon}
返回
Evolving Memristive Reservoir
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3270224.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In light of the dynamic plasticity, nanosize, and energy efficiency of memristors, memristive reservoirs have attracted increasing attention in diverse fields of research recently. However, limited by deterministic hardware implementation, hardware reservoir adaptation is hard to realize. Existing evolutionary algorithms for evolving reservoirs are not designed for hardware implementation. They often ignore the circuit scalability and feasibility of the memristive reservoirs. In this work, based on the reconfigurable memristive units (RMUs), we first propose an evolvable memristive reservoir circuit that is capable of adaptive evolution for varying tasks, where the configuration signals of memristor are evolved directly avoiding the device variance of the memristors. Second, considering the feasibility and scalability of memristive circuits, we propose a scalable algorithm for evolving the proposed reconfigurable memristive reservoir circuit, where the reservoir circuit will not only be valid according to the circuit laws but also has the sparse topology, alleviating the scalability issue and ensuring the circuit feasibility during the evolution. Finally, we apply our proposed scalable algorithm to evolve the reconfigurable memristive reservoir circuits for a wave generation task, six prediction tasks, and one classification task. Through experiments, the feasibility and superiority of our proposed evolvable memristive reservoir circuit are demonstrated.
Keyword:
Reservoirs
Memristors
Hardware
Task analysis
Signal processing algorithms
Scalability
Optimization
Evolution algorithm
evolvable hardware
memristor
neural networks
reservoir computing
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Increased Risk of Chemotherapy-Associated Venous Thromboembolism in Elderly Patients with Cancer
PREAI
分享收藏The bipolar and unipolar reversible behavior on the forgetting memristor model遗忘忆阻器模型的双极和单极可逆行为.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Reservoir computing using dynamic memristors for temporal information processing使用动态忆阻器进行时间信息处理的储层计算NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Nested cross-validation when selecting classifiers is overzealous for most practical applications在大多数实际应用中，选择分类器时的嵌套交叉验证过于热心OAAI
OAAI分享收藏Spoken Digit Classification by In-Materio Reservoir Computing With Neuromorphic Atomic Switch Networks通过神经形态原子开关网络的材料内储层计算进行口语数字分类OAAI
OAAI分享收藏分享收藏Information processing using a single dynamical node as complex system使用单个动态节点作为复杂系统的信息处理NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容