On the implementation of linear diffusion in transconductance‐based cellular nonlinear networks

Abstract

SUMMARYIn theory, cellular nonlinear networks (CNN) are well capable of implementing discrete-space linear diffusion by means of the appropriate templates. In practice, good results have not been demonstrated with transconductance-based circuits. In this paper, we prove that inherent mismatch to very large scale integration implementation is the reason. Although previous works consider that the small perturbations of the network parameters lead to small deviations from the ideal behavior, we consider that this is over optimistic. When interactions between nodes are supported by unidirectional building blocks, originally balanced current paths are realized by mismatched elements. In the case of linear diffusion, the singular location of natural frequencies of the system implies that a small perturbation of balanced current paths renders qualitatively different network dynamics. We analyze and compare a set of linear templates performing unconstrained and constrained linear diffusion in transconductance-based CNN hardware. Several numerical examples are also presented to visualize the consequences of mismatch on the processing. Finally, in order to emphasize the importance of having balanced current paths, we tested the influence of mismatch in a grid built with MOS transistors. In spite of their nonlinearity, the resulting network is much more robust to mismatch. This last result coincides with previous studies.

Approaching object detector mouse retina circuit model analysis and implementation on cellular sensor‐processor array

“…Hence, one can calculate diffusions in separate regions by properly fencing these regions on the mask image. Similar solution can be found in [5].…”

All‐MOS implementation of RC networks for time‐controlled Gaussian spatial filtering

“…Finally, the filtering performed by a resistive grid can be theoretically emulated by the CNN framework [15]. However, the unavoidable mismatch present at any VLSI implementation prevents the typical transconductance-based approach from achieving Gaussian filtering with enough accuracy, specially for large widths [16].…”

Monotonicity of semiflows generated by cooperative delayed full-range CNNs

“…One peculiar aspect of these chips is that they are based on the full-range (FR) model of CNNs [2]- [7]. Differently from the standard (S) CNNs introduced by Chua and Yang [8], where the neuron activations are modeled by a typical threesegment pwl function, FRCNNs exploit hard-limiter devices to limit the allowable range for the time evolution of the neuron state variables.…”