We have examined a role of dynamic synapses in the stochastic Hopfield-like network behavior. Our results demonstrate an appearance of a novel phase characterized by quick transitions from one memory state to another. The network is able to retrieve memorized patterns corresponding to classical ferromagnetic states but switches between memorized patterns with an intermittent type of behavior. T...

For the purpose of realizing a new intelligent system and its simplified VLSI implementation, we propose a new nonvolatile analog memory called “switched diffusion analog memory with feedback circuit (FBSDAM).” FBSDAM has linear writing and erasing characteristics. Therefore, FBSDAM is useful for memorizing an analog value exactly. We also propose a new analog content-addressable memory (CAM) w...

This review of content-addressable memory and as-A. Purpose of This Study sociative computer systems represents an attempt to consolidate and report nontechnically the direction in which numerous independent The primary purpose of this study is to provide in-research programs have progressed during the last ten years. The formation bases on which recommendations can be made paper reflects the v...

The long-term memory of most connectionist systems lies entirely in the weights of the system. Since the number of weights is typically fixed, this bounds the total amount of knowledge that can be learned and stored. Though this is not normally a problem for a neural network designed for a specific task, such a bound is undesirable for a system that continually learns over an open range of doma...

First, this paper derives the prefix sum-of-products expression (PreSOP) and the number of products in a PreSOP for an interval function. Second, it derives Ψ(n, τp), the number of n-variable interval functions that can be represented with τp products. Finally, it shows that more than 99.9% of the n-variable interval functions can be represented with 2n − 1 products, when n is sufficiently larg...

Content-addressable memory (CAM) is a hardware storage commonly used in the fast lookup applications. However, the parallel comparison feature costs the CAM memory large power consumption. In this paper, we propose a new CAM word architecture, called master–slave match line (MSML) design, which aims to combine the master–slave architecture and charge refill minimization technique to reduce the ...

A method for storing analog vectors in Hopfield's continuous feedback model is proposed. By analog vectors we mean vectors whose components are real-valued. The vectors to be stored are set as equilibria of the network. The network model consists of one layer of visible neurons and one layer of hidden neurons. We propose a learning algorithm, which results in adjusting the positions of the equi...

In designing a neural network for content-addressable memory of spatial patterns, large capacity is desirable. In view of dynamical systems, it requires that the model system for the network have large number of stable (retrievable) periodic solutions. Recently, Wu and Zhang [21] considered the following simple discrete network of two identical neurons with excitatory interactions: { x(n) = βx(...

As it was shown earlier, oscillatory networks consisting of limit-cycle oscillators interacting via complex-valued c onnec-tions can be u s e d for associative memory design. Phase memory as a special type of associative memory in oscillatory networks has been invented and studied. Detailed analysis of phase memory features of phasor networks related to oscilla-tory networks has been performed....

The development of elegant matching procedures has significantly improved the search time of a query sequence in a database of molecular sequences. However the architectural limitations of conventional computers allow only one sequence access/retrieval from the database at a time. This paper presents a digital hardware-based solution for fast comparison of molecular sequences.