Tamás Roska

The CNN universal machine: an analogic array computer

A new invention, the cellular neural network (CNN) universal machine and supercomputer, is presented. This is the first algorithmically programmable analog array computer having real-time and supercomputer power on a single chip. The CNN universal machine is described, emphasizing its programmability as well as global and distributed analog memory and logic, high throughput via electromagnetic waves, and complex cells that may be used also for simulating a broad class of PDEs. Its implementation, the CNN universal chip, is also described, along with its use of a multichip supercomputer. Other types of hardware implementations are also briefly discussed. Details of the algorithmic aspects of the new type of analogic (analog logic) algorithms, as well as the analogic software (language, compiler, machine code, etc.) are explained, along with a brief description of the available CNN workstation for implementing and simulating these new concepts. A broad range of applications is reviewed, including neuromorphic computing, programmable physics, programmable chemistry, and programmable bionics. >

Cellular neural networks with non‐linear and delay‐type template elements and non‐uniform grids

The cellular neural network (CNN) paradigm is a powerful framework for analogue non-linear processing arrays placed on a regular grid. In this paper we extend the current repertoire of CNN cloning template elements (atoms) by introducing additional non-linear and delay-type characteristics. In addition, architectures with non-uniform processors and neighbourhoods (grid sizes) are introduced. With this generalization, several well-known and powerful analogue array-computing structures can be interpreted as special cases of the CNN. Moreover, we show that the CNN with these generalized cloning templates has a general programmable circuit structure (a prototype machine) with analogue macros and algorithms. the relations with the cellular automaton (CA) and the systolic array (SA) are analysed. Finally, some robust stability results and the state space structure of the dynamics are presented.

Stability and dynamics of delay-type general and cellular neural networks

Several stability results and additional properties of the delay-type neural network and cellular network dynamics are proved. As a typical example, it is proved that if the feedback and delayed feedback matrices are nonnegative and their sum is irreducible, then the neural network is stable. >

Stability of cellular neural networks with dominant nonlinear and delay-type templates

Presents some further stability results for cellular neural networks (CNNs) with nonlinear delay-type templates. It is shown that there exists a globally asymptotically stable equilibrium point in CNNs with dominant nonlinear delay-type templates. Such a CNN can be used as a pattern classifier or encoder in the sense that there is a nonlinear map that relates the steady state output to the input regardless of the initial conditions. >

Neural Synaptic Weighting With a Pulse-Based Memristor Circuit

A pulse-based programmable memristor circuit for implementing synaptic weights for artificial neural networks is proposed. In the memristor weighting circuit, both positive and negative multiplications are performed via a charge-dependent Ohms law (). The circuit is composed of five memristors with bridge-like connections and operates like an artificial synapse with pulse-based processing and adjustability. The sign switching pulses, weight setting pulses and synaptic processing pulses are applied through a shared input terminal. Simulations are done with both linear memristor and window-based nonlinear memristor models.

The analogic cellular neural network as a bionic eye

The conception of the CNN universal machine has led quite naturally to the invention of the analogic CNN bionic eye (henceforth referred to simply as the bionic eye). the basic idea is to combine the elementary functions, the building blocks, of the retina and other 2 1/2 D sensory organs, algorithmically, in a stored programme of a CNN universal machine, through the use of artificial analogic programmes. the term bionic is defined in a rigorous way: it is a nonlinear, dynamic, spatiotemporal biological model implemented in a stored programme electronic (optoelectronic) device; this device is in our case the analogic CNN universal machine (or chip). The aim of this paper is to report on this new invention, particularly to electronic and computer engineers, in a tutorial way. We begin by summarizing (1) the biological aspects of the range of retinal function (the retinal universe), (2) the CNN paradigm and the CNN universal machine architecture and (3) the general principles of retinal modelling in CNN. Next we describe new CNN circuit and template design innovations that can be used to implement physiological functions in the retina and other sensory organs using the CNN universal machine. Finally we show how to combine given retinal functional elements implemented in the CNN universal machine with analogic algorithms to form the bionic retina. the resulting system can be used not only for simulating biological retinal function but also for generating functions that go far beyond biological capabilities. Several bionic retina functions, different topographic modalities and analogic CNN algorithms can then be combined to form the analogic CNN bionic eye. the qualitative aspects of the models, especially the range of dynamics and accuracy considerations in VLSI optoelectronic implementations, are outlined. Finally, application areas of the bionic eye and possibilities of constructing innovative devices based on this invention (such as the bionic eyeglass or the visual mouse) are described.

Cellular neural networks with nonlinear and delay-type template elements

The cellular neural network (CNN) paradigm is a powerful framework for analog nonlinear processing arrays placed on a regular grid. The authors extend the repertoire of CNN cloning template elements (atoms) by introducing additional nonlinear and delay-type characteristics. With this generalization, several well-known and powerful analog array-computing structures can be interpreted as special cases of the CNN. Moreover, it is shown that the CNN with these generalized cloning templates has a general programmable circuit structure with analog macros and algorithms. The relations with the cellular automaton and the systolic array are analysed. Finally, some robust stability results and the state-space structure of the dynamics are presented.<<ETX>>

Genetic algorithm for CNN template learning

A learning algorithm for space invariant cellular neural networks (CNNs) is described. Learning is formulated as an optimization problem. Exploration of any specified domain of stable CNNs is possible by the current approach. Templates are derived using a genetic optimization algorithm. Details of the algorithm are discussed and several application results are shown. Using this algorithm, propagation-type and gray-scale-output CNNs can also be designed. >

A 0.8-/spl mu/m CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage

This paper presents a CMOS chip for the parallel acquisition and concurrent analog processing of two-dimensional (2-D) binary images. Its processing function is determined by a reduced set of 19 analog coefficients whose values are programmable with 7-b accuracy. The internal programming signals are analog, but the external control interface is fully digital. On-chip nonlinear digital-to-analog converters (DACs) map digitally coded weight values into analog control signals, using feedback to predistort their transfer characteristics in accordance to the response of the analog programming circuitry. This strategy cancels out the nonlinear dependence of the analog circuitry with the programming signal and reduces the influence of interchip technological parameters random fluctuations. The chip includes a small digital RAM memory to store eight sets of processing parameters in the periphery of the cell array and four 2-D binary images spatially distributed over the processing array. It also includes the necessary control circuitry to realize the stored instructions in any order and also to realize programmable logic operations among images. The chip architecture is based on the cellular neural/nonlinear network universal machine (CNN-UM). It has been fabricated in a 0.8-/spl mu/m single-poly double-metal technology and features 2-/spl mu/s operation speed (time required to process an image) and around 7-b accuracy in the analog processing operations.

Memristor Bridge Synapses

In this paper, we propose a memristor bridge circuit consisting of four identical memristors that is able to perform zero, negative, and positive synaptic weightings. Together with three additional transistors, the memristor bridge weighting circuit is able to perform synaptic operation for neural cells. It is compact as both weighting and weight programming are performed in a memristor bridge synapse. It is power efficient, since the operation is based on pulsed input signals. Its input terminals are utilized commonly for applying both weight programming and weight processing signals via time sharing. In this paper, features of the memristor bridge synapses are investigated using the TiO memristor model via simulations.