Adaptive Bidirectional Associative Memory Research Articles

Analysis on Feelings for Designs

Abstract The objects of data processing in this research are adjectives such as innovative, bright, elegant or cheerfixl expressed by people who are just selecting goods to purchase. The subjective data obtained by a product rating usually has a big variance reflecting vagueness, non-linearity or non-additivity of the feelings of people. Such data should be considered as fuzzy data as well as statistical data. In this paper, a method of constructing a fuzzy factor space is suggested. One of the problems here is how to define the second moment of fuzzy data. After defining a fuzzy metric space, a covering problem is formulated to detect representative adjectives that are used with relatively small differences between people. Finally, the problem of identifying a relation between selected adjectives and pre-selected designs is considered by using a multi-channel adaptive bidirectional associative memory.

Multilayer neural network of adaptive bidirectional associative memories

The analysis of the functioning of the brain allows to propose a computational model of multilayer artificial neural network susceptible of associating some response to a particular input, so that when we present that input, we get the required output by the stability of its states and by minimizing the function of energy of the network. The problem of explosion in the number of interconnections has been solved by the introduction of a layer between the input and the output layer of the network. In this paper, we propose the adaptive bidirectional associative memory by conjugate gradient algorithm, so as to study the behavior and performances of the network on pairs of patterns through using the autoassociative or heteroassociative memories.

A parallel processing VLSI BAM engine

In this paper emerging parallel/distributed architectures are explored for the digital VLSI implementation of adaptive bidirectional associative memory (BAM) neural network. A single instruction stream many data stream (SIMD)-based parallel processing architecture, is developed for the adaptive BAM neural network, taking advantage of the inherent parallelism in BAM. This novel neural processor architecture is named the sliding feeder BAM array processor (SLiFBAM). The SLiFBAM processor can be viewed as a two-stroke neural processing engine, It has four operating modes: learn pattern, evaluate pattern, read weight, and write weight. Design of a SLiFBAM VLSI processor chip is also described. By using 2-mum scalable CMOS technology, a SLiFBAM processor chip with 4+4 neurons and eight modules of 256x5 bit local weight-storage SRAM, was integrated on a 6.9x7.4 mm(2) prototype die. The system architecture is highly flexible and modular, enabling the construction of larger BAM networks of up to 252 neurons using multiple SLiFBAM chips.

A CMOS analog adaptive BAM with on-chip learning and weight refreshing

The transconductance-mode (T-mode) approach is extended to implement analog continuous-time neural network hardware systems to include on-chip Hebbian learning and on-chip analog weight storage capability. The demonstration vehicle used is a 5+5-neuron bidirectional associative memory (BAM) prototype fabricated in a standard 2-mum double-metal double-polysilicon CMOS process. Mismatches and nonidealities in learning neural hardware are not supposed to be critical if on-chip learning is available, because they will be implicitly compensated. However, mismatches in the learning circuits themselves cannot always be compensated. This mismatch is specially important if the learning circuits use transistors operating in weak inversion. The authors estimate the expected mismatch between learning circuits in the BAM network prototype and evaluate its effect on the learning performance, using theoretical computations and Monte Carlo HSPICE simulations. These theoretical predictions are verified using experimentally measured results on the test vehicle prototype.

Structural stability of unsupervised learning in feedback neural networks

Structural stability is proved for a large class of unsupervised nonlinear feedback neural networks, adaptive bidirectional associative memory (ABAM) models. The approach extends the ABAM models to the random-process domain as systems of stochastic differential equations and appends scaled Brownian diffusions. It is also proved that this much larger family of models, random ABAM (RABAM) models, is globally stable. Intuitively, RABAM equilibria equal ABAM equilibria that vibrate randomly. The ABAM family includes many unsupervised feedback and feedforward neural models. All RABAM models permit Brownian annealing. The RABAM noise suppression theorem characterizes RABAM system vibration. The mean-squared activation and synaptic velocities decrease exponentially to their lower hounds, the respective temperature-scaled noise variances. The many neuronal and synaptic parameters missing from such neural network models are included, but as net random unmodeled effects. They do not affect the structure of real-time global computations.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Bart Kosko, Adaptive bidirectional associative memories, APPLIED OPTICS, Vol.26,No.3(1987)

Bart Kosko, Adaptive bidirectional associative memories, APPLIED OPTICS, Vol.26,No.3(1987)

Unsupervised learning in noise

A new hybrid learning law, the differential competitive law, which uses the neuronal signal velocity as a local unsupervised reinforcement mechanism, is introduced, and its coding and stability behavior in feedforward and feedback networks is examined. This analysis is facilitated by the recent Gluck-Parker pulse-coding interpretation of signal functions in differential Hebbian learning systems. The second-order behavior of RABAM (random adaptive bidirectional associative memory) Brownian-diffusion systems is summarized by the RABAM noise suppression theorem: the mean-squared activation and synaptic velocities decrease exponentially quickly to their lower bounds, the instantaneous noise variances driving the system. This result is extended to the RABAM annealing model, which provides a unified framework from which to analyze Geman-Hwang combinatorial optimization dynamical systems and continuous Boltzmann machine learning.

Adaptive bidirectional associative memories

Bidirectionality, forward and backward information flow, is introduced in neural networks to produce two-way associative search for stored stimulus-response associations (A(i),B(i)). Two fields of neurons, F(A) and F(B), are connected by an n x p synaptic marix M. Passing information through M gives one direction, passing information through its transpose M(T) gives the other. Every matrix is bidirectionally stable for bivalent and for continuous neurons. Paired data (A(i),B(i)) are encoded in M by summing bipolar correlation matrices. The bidirectional associative memory (BAM) behaves as a two-layer hierarchy of symmetrically connected neurons. When the neurons in F(A) and F(B) are activated, the network quickly evolves to a stable state of twopattern reverberation, or pseudoadaptive resonance, for every connection topology M. The stable reverberation corresponds to a system energy local minimum. An adaptive BAM allows M to rapidly learn associations without supervision. Stable short-term memory reverberations across F(A) and F(B) gradually seep pattern information into the long-term memory connections M, allowing input associations (A(i),B(i)) to dig their own energy wells in the network state space. The BAM correlation encoding scheme is extended to a general Hebbian learning law. Then every BAM adaptively resonates in the sense that all nodes and edges quickly equilibrate in a system energy local minimum. A sampling adaptive BAM results when many more training samples are presented than there are neurons in F(B) and F(B), but presented for brief pulses of learning, not allowing learning to fully or nearly converge. Learning tends to improve with sample size. Sampling adaptive BAMs can learn some simple continuous mappings and can rapidly abstract bivalent associations from several noisy gray-scale samples.

Designs and devices for optical bidirectional associative memories

The bidirectional associative memory (BAM) is a powerful neural network paradigm that is well suited to optical implementation. The BAM is heteroassociative (of which autoassociative operation is a special case) and is guaranteed to converge to a stable final state regardless of the connection weight matrix used. The BAM is placed in a conceptual framework that facilitates comparison with other neural network models. Variations on the BAM such as the bidirectional optimal memory (BOM), the competitive BAM (CBAM), and the adaptive BAM (ABAM) indicate some of the interesting directions this simple structure may evolve, leading in a natural progression toward the power of a model such as the Carpenter-Grossberg ART. The simplicity of the BAM invites uncomplicated optical implementations. BAM designs based on optical matrix-vector multipliers (MVMs) and on volume holographic connections are presented. Spatial light modulator (SLM) device designs currently under development to support the MVM BAMs are given.