PSECMAC: A Novel Self-Organizing Multiresolution Associative Memory Architecture

Abstract

The cerebellum constitutes a vital part of the human brain system that possesses the capability to model highly nonlinear physical dynamics. The cerebellar model articulation controller (CMAC) associative memory network is a computational model inspired by the neurophysiological properties of the cerebellum, and it has been widely used for control, optimization, and various pattern recognition tasks. However, the CMAC network's highly regularized computing structure often leads to the following: 1) a suboptimal modeling accuracy, 2) poor memory utilization, and 3) the generalization-accuracy dilemma. Previous attempts to address these shortcomings have limited success and the proposed solutions often introduce a high operational complexity to the CMAC network. This paper presents a novel neurophysiologically inspired associative memory architecture named pseudo-self-evolving CMAC (PSECMAC) that nonuniformly allocates its computing cells to overcome the architectural deficiencies encountered by the CMAC network. The nonuniform memory allocation scheme employed by the proposed PSECMAC network is inspired by the cerebellar experience-driven synaptic plasticity phenomenon observed in the cerebellum, where significantly higher densities of synaptic connections are located in the frequently accessed regions. In the PSECMAC network, this biological synaptic plasticity phenomenon is emulated by employing a data-driven adaptive memory quantization scheme that defines its computing structure. A neighborhood-based activation process is subsequently implemented to facilitate the learning and computation of the PSECMAC structure. The training stability of the PSECMAC network is theoretically assured by the proof of its learning convergence, which will be presented in this paper. The performance of the proposed network is subsequently benchmarked against the CMAC network and several representative CMAC variants on three real-life applications, namely, pricing of currency futures option, banking failure classification, and modeling of the glucose-insulin dynamics of the human glucose metabolic process. The experimental results have strongly demonstrated the effectiveness of the PSECMAC network in addressing the architectural deficiencies of the CMAC network by achieving significant improvements in the memory utilization, output accuracy as well as the generalization capability of the network.

An intelligent CMAC-PD torque controller with anti-over-learning scheme for electric load simulator

“…Current research is mainly focused on the convergence of the CMAC for function approximation (Lin and Chiang, 1997;Teddy et al, 2007), but our simulation showed that the convergence conditions on the learning rate of the CMAC for function approximation does not apply to the control system. Although the existing literature gave various improvements on CMAC (Cao and Tu, 2012;Cheng, 2011;Teddy et al, 2008), most of them focus on theoretical analysis and simulation. These methods still cannot meet the requirements of practical implementation of a CMAC-PD controller for electric load simulators due to the over-learning problem of the CMAC.…”

Reduced order multiport parallel and multidirectional neural associative memories

“…The human brain is the underlying biological structure that is responsible for human intelligence. It has complex networks of neurons which collaborate in a highly nonlinear manner to create a massive information processing systems (Teddy et al 2008). Therefore, there has always been a great interest to mimic brain-like information processing characteristics that are critical to develop such intelligent information processing systems.…”

“…However, the brain has highly complex, nonlinear, dynamic and evolutionary structure that makes it extremely difficult to model these properties. The cerebellum is one brain region located at the bottom rear of the head in which neuronal connectivity is sufficiently regular to facilitate the learning and associative memory functions and employs error correction signals to drive the network learning and memory tasks (Teddy et al 2008). However, there are several major architectural limitations are associated with cerebellar models.…”

A novel neuro-cognitive approach to modeling traffic control and flow based on fuzzy neural techniques

“…Centre of Computational Intelligence undertakes active research in intelligent neuro-fuzzy systems for the modeling of complex, nonlinear and dynamic problem domains. Examples of neural and neuro-fuzzy systems developed are Modified Cerebellar Articulation Controller (MCMAC) (Ang & Quek, 2000;Teddy, Lai, & Quek, 2007;Teddy, Quek, & Lai, 2008), Generic Self-organizing Fuzzy Neural Network (GenSoFNN) , Falcon-like Fuzzy Neural Networks (Quek, Tan, & Sagar, 2001;Quah, Quek, & Leedham, 2005), RSPOP:Rough-Set based Psuedo-Outer Product Fuzzy Neural Network (Ang & Quek, 2005), TSK fuzzy neural network (Wang, Quek, & Ng, 2004;Tang, Quek, & Ng, 2005) and Pseudo Outer-Product based Fuzzy Neural Network (POPFNN) (Zhou & Quek, 1996;Quek & Zhou, 1999;Quek & Zhou, 2001;Wang et al, 2004;Singh, Quek, & Cho, 2008). These have been applied to novel and interesting applications such as automated driving (Pasquier, Quek, & Toh, 2001), signature forgery detection (Quek & Zhou, 2002), gear control for automotive continuous variable transmission (Ang, Quek, & Wahab, 2002), Bank failure and finance analysis (Tung, Quek, & Cheng, 2004;Huang, Pasquier, & Quek, 2008), medical data analysis (Tung & Quek, 2005;Tan, Quek, & Ng, 2005;Tan, Quek, Ng, & Ravzi, 2008) and fingerprint verification (Zhou, Quek, & Ng, 1995;Quek & Zhou, 2001).…”