Adaptive Memory-enhanced Time Delay Reservoir and Its Memristive Implementation

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{Shi:ieeeTC,

• author = "Xinming Shi and Leandro L. Minku and Xin Yao",
• title = "Adaptive Memory-enhanced Time Delay Reservoir and Its Memristive Implementation",
• journal = "IEEE Transactions on Computers",
• year = "2022",
• volume = "71",
• number = "11",
• pages = "2766--2777",
• keywords = "genetic algorithms, genetic programming, Time Delay Reservoir, memristor, time series prediction",
• ISSN = "0018-9340",
• DOI = "doi:10.1109/TC.2022.3173151",
• size = "11 pages",
• abstract = "Time Delay Reservoir (TDR) is a hardware-friendly machine learning approach from two perspectives. First, it can prevent the connection overhead of neural networks with increasing neurons. Second, through its dynamic system representation, it can also be implemented in hardware by different systems. However, it performs poorly on tasks that involve long-term dependency. In this work, we first introduce a higher-order delay unit, which is capable to accumulate and transfer the long history states in an adaptive manner to further enhance the reservoir memory. Particle Swarm Optimisation is applied to optimize the enhanced degree of memory adaptivity and also decouple the different given tasks. Our experiments demonstrate its superiority both for short- and long-term memory datasets over seven existing approaches. In light of hardware-friendly feature of TDR, we further propose a memristive implementation of our adaptive memory-enhanced TDR, where a dynamic memristor and the memristor-based delay element are applied to construct the reservoir. Through circuit simulation, the feasibility of our proposed memristive implementation is verified. The comparisons with different hardware reservoirs show that our proposed memristive implementation is effective both for short- and long-term memory datasets, while exhibiting benefits in terms of smaller circuit area and lower power consumption compared with traditional hardware reservoirs.",
• notes = "also known as \cite{9773007}",

}

Genetic Programming entries for Xinming Shi Leandro L Minku Xin Yao

Citations