Complex Learning in Bio-plausible Memristive Networks
Citations Over TimeTop 10% of 2015 papers
Abstract
The emerging memristor-based neuromorphic engineering promises an efficient computing paradigm. However, the lack of both internal dynamics in the previous feedforward memristive networks and efficient learning algorithms in recurrent networks, fundamentally limits the learning ability of existing systems. In this work, we propose a framework to support complex learning functions by introducing dedicated learning algorithms to a bio-plausible recurrent memristive network with internal dynamics. We fabricate iron oxide memristor-based synapses, with well controllable plasticity and a wide dynamic range of excitatory/inhibitory connection weights, to build the network. To adaptively modify the synaptic weights, the comprehensive recursive least-squares (RLS) learning algorithm is introduced. Based on the proposed framework, the learning of various timing patterns and a complex spatiotemporal pattern of human motor is demonstrated. This work paves a new way to explore the brain-inspired complex learning in neuromorphic systems.
Related Papers
- → A Dynamical Compact Model of Diffusive and Drift Memristors for Neuromorphic Computing(2021)40 cited
- → Observation and characterization of memristor current spikes and their application to neuromorphic computation(2012)25 cited
- → Determining optimal switching speed for memristors in neuromorphic system(2015)20 cited
- → A Dynamical Compact Model of Diffusive and Drift Memristors for Neuromorphic Computing (Adv. Electron. Mater. 8/2022)(2022)8 cited
- → Editorial Special Issue for 50th Birthday of Memristor Theory and Application of Neuromorphic Computing Based on Memristor—Part I(2021)12 cited