Neural networks and their applications in component design data retrieval

Neural networks have gained increased importance in the past few years. One of the basic characteristics of neural networks is the property of associative memory. In this paper we study the possibility of using the ideas of neural networks and associative memory in the manufacturing domain, with specific reference to design data retrieval in group technology. A two-layer feed-forward perceptron with backpropagation is simulated on a Vax-8550 to train example parts. The complete scheme along with the simulation results are explained and future directions indicated.     

CLAM: A new model of associative memory

We present a new associative memory model that stores arbitrary bipolar patterns without the problems we can find in other models like BAM or LAM. After identifying those problems we show the new memory topology and we explain its learning and recall stages. Mathematical demonstrations are provided to prove that the new memory model guarantees the perfect retrieval of every stored pattern and also to prove that whatever the input of the memory is, it operates as a nearest neighbor classifier. ©2000 John Wiley & Sons, Inc.     

Cognitive Principles for Information Management: The Principles of Mnemonic Associative Knowledge (P-MAK)

Information management systems improve the retention of information in large collections. As such they act as memory prostheses, implying an ideal basis in human memory models. Since humans process information by association, and situate it in the context of space and time, systems should maximize their effectiveness by mimicking these functions. Since human attentional capacity is limited, systems should scaffold cognitive efforts in a comprehensible manner. We propose the Principles of Mnemonic Associative Knowledge (P-MAK), which describes a framework for semantically identifying, organizing, and retrieving information, and for encoding episodic events by time and stimuli. Inspired by prominent human memory models, we propose associative networks as a preferred representation. Networks are ideal for their parsimony, flexibility, and ease of inspection. Networks also possess topological properties—such as clusters, hubs, and the small world—that aid analysis and navigation in an information space. Our cognitive perspective addresses fundamental problems faced by information management systems, in particular the retrieval of related items and the representation of context. We present evidence from neuroscience and memory research in support of this approach, and discuss the implications of systems design within the constraints of P-MAK’s principles, using text documents as an illustrative semantic domain.

Associative processing and processors

Associative memory concerns the concept that one idea may trigger the recall of a different but related idea. Traditional computers, however, rely upon a memory design that stores and retrieves data by its address rather than its content. In such a search, every accessed data word must travel individually between the processing unit and the memory. The simplicity of this retrieval-by-address approach has ensured its success, but has also produced some inherent disadvantages. One is the von Neumann bottleneck, where the memory-access path becomes the limiting factor for system performance. A related disadvantage is the inability to proportionally increase the size of a unit transfer between the memory and the processor as the size of the memory scales up. Associative memory, in contrast, provides a naturally parallel and scalable form of data retrieval for both structured data (e.g. sets, arrays, tables, trees and graphs) and unstructured data (raw text and digitized signals). An associative memory can be easily extended to process the retrieved data in place, thus becoming an associative processor. This extension is merely the capability for writing a value in parallel into selected cells     

On the synthesis of brain-state-in-a-box neural models with application to associative memory

In this article we present techniques for designing associative memories to be implemented by a class of synchronous discrete-time neural networks based on a generalization of the brain-state-in-a-box neural model. First, we address the local qualitative properties and global qualitative aspects of the class of neural networks considered. Our approach to the stability analysis of the equilibrium points of the network gives insight into the extent of the domain of attraction for the patterns to be stored as asymptotically stable equilibrium points and is useful in the analysis of the retrieval performance of the network and also for design purposes. By making use of the analysis results as constraints, the design for associative memory is performed by solving a constraint optimization problem whereby each of the stored patterns is guaranteed a substantial domain of attraction. The performance of the designed network is illustrated by means of three specific examples.     

Phase change memory

Phase change memory (PCM) is a non-volatile solid-state memory technology based on the large resistivity contrast between the amorphous and crystalline states in phase change materials. We present the physics behind this large resistivity contrast and describe how it is being exploited to create high density PCM. We address the challenges facing this technology, including the design of PCM cells, fabrication, device variability, thermal cross-talk and write disturb. We discuss the scalability, assess the pe...     

Two steps micromoulding and photopolymer high-aspect ratio structuring for applications in piezoelectric motor components

 We report on recent advances in micro fabrication technology using micromoulding and high-aspect ratio structuring of photopolymer. The direct application is the realization of components for millimeter-size, ultrasonic piezoelectric motors. A new fabrication process using a thick epoxy-based material (SU-8) and the electroplating of nickel is demonstrated. Photopolymer structures have also been realized and released using a positive tone resist as sacrificial layer. The main advantages over past fabrication methods are better design flexibility, simplicity of the fabrication process, the capability to combine metallic materials (Ni) with polymeric materials (SU-8), and the use of positive tone resist as a sacrificial layer. Received: 25 August 1997/Accepted: 23 October 1997     

Active material micro-actuator arrays fabricated with SU-8 resin

 Active materials such as piezoelectric ceramics and shape memory metal alloys commonly actuate active control and intelligent material systems. Commercially available piezoelectric materials exhibit small actuation stroke and shape memory metal alloys have limited bandwidth. The proposed micro-actuator array design and fabrication process increases the actuation stroke of piezoceramic material by a factor of 1.5 for a 2 × 2 array; two active material segments connected in parallel and two in series, and doubles the response time of a 1 × 4 shape memory alloy driven array; four active materials segments connected in series. A high aspect ratio fabrication method incorporating SU-8 resin and conventional lithography is the process that forms the array linkages. The SU-8 resin array structures are 300 μm tall.     

Neural associative memory for brain modeling and information retrieval

This work concisely reviews and unifies the analysis of different variants of neural associative networks consisting of binary neurons and synapses (Willshaw model). We compute storage capacity, fault tolerance, and retrieval efficiency and point out problems of the classical Willshaw model such as limited fault tolerance and restriction to logarithmically sparse random patterns. Then we suggest possible solutions employing spiking neurons, compression of the memory structures, and additional cell layers. Finally, we discuss from a technical perspective whether distributed neural associative memories have any practical advantage over localized storage, e.g., in compressed look-up tables.     

Some experiments on human memory and a new neural model

An associative memory with parallel architecture is presented. The neurons are modelled by perceptrons having only binary, rather than continuous valued input. To store m elements each having n features, m neurons each with n connections are needed. The n features are coded as an n-bit binary vector. The weights of the n connections that store the n features of an element has only two values -1 and 1 corresponding to the absence or presence of a feature. This makes the learning very simple and straightforward. For an input corrupted by binary noise, the associative memory indicates the element that is closest (in terms of Hamming distance) to the noisy input. In the case where the noisy input is equidistant from two or more stored vectors, the associative memory indicates two or more elements simultaneously. From some simple experiments performed on the human memory and also on the associative memory, it can be concluded that the associative memory presented in this paper is in some respect more akin to a human memory than a Hopfield model.     

A B-spline-based approach to heterogeneous objects design and analysis

The recent advancement of solid freeform fabrication, design techniques and fundamental understanding of material properties in functionally graded materials has made it possible to design and fabricate multifunctional heterogeneous objects. In this paper, we present an integrated design and analysis approach for heterogeneous object realization, which employs a unified design and analysis model based on B-spline representation and allows for direct interaction between the design and analysis model without laborious meshing operation. In the design module, a new approach for intuitively modelling of multi-material objects, termed heterogeneous lofting, is presented. In the analysis module, a novel graded B-spline finite element solution procedure is described, which gives orders of magnitude of better convergence rate in comparison with current methods, as demonstrated in several case studies. Further advantages of this approach include simplified mesh construction, exact geometry/material composition representation and easy extraction of an isomaterial surface for manufacturing process planning.     

Part 3: Brain science, information science and associative memory model

I review recent progress on the associative memory model, which is a kind of neural network model. First, I introduce this model and a mathematical theory called statistical neurodynamics describing its properties. Next, I discuss an associative memory model with hierarchically correlated memory patterns. Initially, in this model, the state approaches a mixed state that is a superposition of memory patterns. After that, it diverges from the mixed state, and finally converges to a memory pattern. I show that this retrieval dynamics can qualitatively replicate the temporal dynamics of face-responsive neurons in the inferior temporal cortex, which is considered to be the final stage of visual perception in the brain. Finally, I show an unexpected link between associative memory and mobile phones (CDMA). The mathematical structure of the CDMA multi-user detection problem resembles that of the associative memory model. It enables us to apply a theoretical framework of the associative memory model to CDMA.     

Characteristics of multidimensional holographic associative memoryin retrieval with dynamically localizable attention

This paper presents the performance analysis of multidimensional holographic associative memory (MHAC). MHAC has the unique ability to retrieve pattern-associations with changeable attention. In attention actuated retrieval the user can dynamically select any subset of the elements in the example query pattern and expect the memory to confine its associative match only within the specified field of attention. MHAC, with the unique ability of localizable attention, can retrieve information correctly even with cues as small as 10% of the query frame. This paper investigates the performance of MHAC in attention actuated retrieval both analytically and experimentally. Besides confirmation, the experiments also identify an operational range space for this memory within which various attention based applications can be built with a performance guarantee.     

Recurrent correlation associative memories

A model for a class of high-capacity associative memories is presented. Since they are based on two-layer recurrent neural networks and their operations depend on the correlation measure, these associative memories are called recurrent correlation associative memories (RCAMs). The RCAMs are shown to be asymptotically stable in both synchronous and asynchronous (sequential) update modes as long as their weighting functions are continuous and monotone nondecreasing. In particular, a high-capacity RCAM named the exponential correlation associative memory (ECAM) is proposed. The asymptotic storage capacity of the ECAM scales exponentially with the length of memory patterns, and it meets the ultimate upper bound for the capacity of associative memories. The asymptotic storage capacity of the ECAM with limited dynamic range in its exponentiation nodes is found to be proportional to that dynamic range. Design and fabrication of a 3-mm CMOS ECAM chip is reported. The prototype chip can store 32 24-bit memory patterns, and its speed is higher than one associative recall operation every 3 mus. An application of the ECAM chip to vector quantization is also described.     

Selective retrieval of memory and concept sequences throughneuro-windows

Presents a crosscorrelational associative memory model which realizes selective retrieval of pattern sequences. When hierarchically correlated sequences are memorized, sequences of the correlational centers can be defined as the concept sequences. The authors propose a modified neuro-window method which enables selective retrieval of memory sequences and concept sequences. It is also shown that the proposed model realizes capacity expansion of the memory which stores random sequences.     

Continuous classifying associative memory

In this article we present the so‐called continuous classifying associative memory, able to store continuous patterns avoiding the problems of spurious states and data dependency. This is a memory model based on our previously developed classifying associative memory, which enables continuous patterns to be stored and recovered. We will also show that the behavior of this continuous classifying associative memory may be adjusted to some predetermined goals by selecting some internal operating functions. © 2002 Wiley Periodicals, Inc.     

Extension from a linear associative memory to a linguistic linear associative memory

We present a linguistic extension from a crisp model by using a codification model that allows us to implement a fuzzy system on a discrete decision model. The paper begins with an introduction to the representation of fuzzy information, followed by a discussion of the codification method and the extension of a linear associative memory to a linguistic linear associative memory. Finally, we enumerate the advantages and disadvantages of the obtained linguistic linear associative memory. © 1998 John Wiley & Sons, Inc.13: 41–57, 1998     

神经网络的混沌运动与控制

本文采用一种由混沌神经元构成的联想记忆神经网络．以混沌神经网络为基础,研究其非线 性动力学特性、混沌吸引子轨迹以及对初始条件的敏感性, 实现混沌神经网络的动态联想记 忆功能．在网络输入发生较大变异情况下所发生的失忆,本文采用时空系统混沌控制的钉扎 反馈方法,使网络恢复记忆．上述研究通过对异步电动机故障的动态记忆和恢复控制的仿真 实验得到证实．本文研究结果表明,在国内外对神经网络混沌控制研究的热点中,时空系统 的钉扎反馈控制是一种值得推荐的方法;神经网络的混沌控制扩大了网络的容错性,进而提 高了混沌神经网络的实用性,这将在复杂模式识别,图象处理等工程上具有广阔的应用前景 ．     

Cache consistency by design

Summary. In this paper we present a proof of the sequential consistency of the lazy caching protocol of Afek, Brown, and Merritt. The proof will follow a strategy of stepwise refinement, developing the distributed caching memory in five transformation steps from a specification of the serial memory, whilst preserving the sequential consistency in each step. The proof, in fact, presents a rationalized design of the distributed caching memory. We will carry out our proof using a simple process-algebraic formalism for the specification of the various design stages. We will not follow a strictly algebraic exposition, however. At some points the correctness will be shown using direct semantic arguments, and we will also employ higher-order constructs like action transducers to relate behaviours. The distribution of the design/proof over five transformation steps provides a good insight into the variations that could have been allowed at each point of the design while still maintaining sequential consistency. The design/proof in fact establishes the correctness of a whole family of related memory architectures. The factorization in smaller steps also allows for a closer analysis of the fairness assumptions about the distributed memory.     

A Web-based collaborative filtering system

In this paper we describe a collaborative filtering system for automatically recommending high-quality information to users with similar interests on arbitrarily narrow information domains. It asks a user to rate a gauge set of items. It then evaluates the user's rates and suggests a recommendation set of items. We interpret the process of evaluation as an inference mechanism that maps a gauge set to a recommendation set. We accomplish the mapping with fuzzy associative memory. We implemented the suggested system in a Web server and tested its performance in the domain of retrieval of technical papers, especially in the field of information technologies. The experimental results show that it may provide reliable recommendations.