Cellular neural networks based on resonant tunnelling diodes

Abstract

SUMMARYResonant tunnelling diodes (RTDs) have intriguing properties which make them a primary nanoelectronic device for both analogue and digital applications. We propose two di erent types of RTD-based cells for the cellular neural network (CNN) which exhibit superior performance in terms of complexity, functionality, or processing speed compared to standard cells. In the ÿrst cell model, the resistor of the standard cell is replaced by an RTD, which results in a more compact and versatile cell which requires neither self-feedback nor a non-linear output function, and allows three stable equilibrium points. If a resonant tunnelling transistor (RTT) is used instead of the RTD, the dynamics can be controlled through its gate voltage as an additional network parameter. In a majority of CNN applications, bistable cells are su cient. Utilizing RTD-based bistable logic elements to store the state of the cell, switching occurs almost instantaneously as virtually no charge transfer is necessary, and it is possible to implement non-linear connections in a straightforward manner. Hence, it turns out that RTD-based CNNs are tailor-made for the implementation of extremely fast bipolar operations and non-linear templates. The ideas presented in this paper may also be beneÿcially applied to other types of circuits and systems such as A=D converters or sigma-delta modulators.

Distributed Sensor Networks: A Cellular Nonlinear Network Perspective

“…CNNs based on resonant tunneling diodes 73 or quantum dots 74,75,76 are the first examples of such nanonets. The wireless nanonets we envision have the potential to surpass the barrier of 1mm 3 per node, thus coming even closer to real smart dust.…”

Programmable quantum-dots memristor based architecture for image processing

“…In [9] RTDs have been introduced as variable resistors to introduce versatility and compactness to CNN unit cells. In [10] A CNN architecture employing RTDs is investigated for its operation and it is shown that RTDs support fast settling times for various image processing applications.…”

Stable Patterns Realized by a Class of One-Dimensional Two-Layer CNNs

“…However, as far as the standard CNN model [1] is concerned, there is a limitation on the signal processing capability due to its simple structure. To overcome this difficulty, various extensions of the model have been proposed so far, e.g., multilayer CNNs [1], [4]- [7], nonlinear templates [8], CNN universal machines [9], universal CNN cells [10], RTD-CNNs [11], and so on.…”