首页|Research Data from University of Dayton Update Understanding of Liquid State Mac hines (Memristor Based Liquid State Machine With Method for In-situ Training)
Research Data from University of Dayton Update Understanding of Liquid State Mac hines (Memristor Based Liquid State Machine With Method for In-situ Training)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Li quid State Machines. According to news originating from Dayton, Ohio, by NewsRx correspondents, research stated, "Spiking neural network (SNN) hardware has gain ed significant interest due to its ability to process complex data in size, weig ht, and power (SWaP) constrained environments. Memristors, in particular, offer the potential to enhance SNN algorithms by providing analog domain acceleration with exceptional energy and throughput efficiency." Our news journalists obtained a quote from the research from the University of D ayton, "Among the current SNN architectures, the Liquid State Machine (LSM), a f orm of Reservoir Computing (RC), stands out due to its low resource utilization and straightforward training process. In this paper, we present a custom memrist or-based LSM circuit design with an online learning methodology. The proposed ci rcuit implementing the LSM is designed using SPICE to ensure precise device leve l accuracy. Furthermore, we explore liquid connectivity tuning to facilitate a r eal-time and efficient design process. To assess the performance of our system, we evaluate it on multiple datasets, including MNIST, TI-46 spoken digits, acous tic drone recordings, and musical MIDI files. Our results demonstrate comparable accuracy while achieving significant power and energy savings when compared to existing LSM accelerators. Moreover, our design exhibits resilience in the prese nce of noise and neuron misfires."
DaytonOhioUnited StatesNorth and C entral AmericaEmerging TechnologiesLiquid State MachinesMachine LearningUniversity of Dayton
NETL
NSTL
