Evolving Local Plasticity Rules for Synergistic Learning in Echo State Networks

• Published in: IEEE transaction on neural networks and learning systems Vol. 31; no. 4; pp. 1363 - 1374
• Main Authors: Wang, Xinjie, Jin, Yaochu, Hao, Kuangrong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Biological neural networks; Classification; Correlation; Covariance matrix; covariance matrix adaptation evolution strategy (ES); Decorrelation; echo state networks (ESNs); Learning; local synaptic plasticity; Neural plasticity; Neurons; Optimization; Parameters; regression; Reservoirs; Synaptic plasticity; synergistic learning
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2019.2919903

Existing synaptic plasticity rules for optimizing the connections between neurons within the reservoir of echo state networks (ESNs) remain to be global in that the same type of plasticity rule with the same parameters is applied to all neurons. However, this is biologically implausible and practically inflexible for learning the structures in the input signals, thereby limiting the learning performance of ESNs. In this paper, we propose to use local plasticity rules that allow different neurons to use different types of plasticity rules and different parameters, which are achieved by optimizing the parameters of the local plasticity rules using the evolution strategy (ES) with covariance matrix adaptation (CMA-ES). We show that evolving neural plasticity will result in a synergistic learning of different plasticity rules, which plays an important role in improving the learning performance. Meanwhile, we show that the local plasticity rules can effectively alleviate synaptic interferences in learning the structure in sensory inputs. The proposed local plasticity rules are compared with a number of the state-of-the-art ESN models and the canonical ESN using a global plasticity rule on a set of widely used prediction and classification benchmark problems to demonstrate its competitive learning performance.