A piecewise-linear simplicial coupling cell for CNN gray-level image processing

In this paper, we propose a universal piecewise-linear (PWL) CNN coupling cell, the simplicial cell, which is intended to work with binary as well as gray-level inputs. The construction of the cell is based on the theory of canonical simplicial PWL representations. As a consequence, the coupling function is endowed with important numerical features, namely: the representation of the characteristic cell function is sparse; the family of coupling functions constitutes a Hilbert space; powerful solution algorithms have been developed for the approximation of nonlinear functions, which is particularly useful when the CNN parameters need to be tuned from examples; the parameters can be extracted from a truth table when the CNN is specified analytically.

[1]  Hongil Yoon,et al.  A 4 Gb DDR SDRAM with gain-controlled pre-sensing and reference bitline calibration schemes in the twisted open bitline architecture , 2001, 2001 IEEE International Solid-State Circuits Conference. Digest of Technical Papers. ISSCC (Cat. No.01CH37177).

[2]  R. Dogaru,et al.  Physical modeling of RTD-based CNN cells , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[3]  Leon O. Chua,et al.  Pyramidal cells: a novel class of adaptive coupling cells and their applications for cellular neural networks , 1998 .

[4]  P. Marinucci,et al.  VLSI implementation of a modular and programmable neural architecture , 1994, Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems.

[5]  O. Agamennoni,et al.  A sparse method for the canonical representation and approximation of PWL functions , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[6]  P. Julián,et al.  High-level canonical piecewise linear representation using a simplicial partition , 1999 .

[7]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[8]  Åke Björck,et al.  Numerical methods for least square problems , 1996 .

[9]  Leon O. Chua,et al.  Efficient implementation of neighborhood logic for cellular automata via the Cellular Neural Network Universal Machine , 1997 .

[10]  Min Li,et al.  A 150 MHz graphics rendering processor with 256 Mb embedded DRAM , 2001, 2001 IEEE International Solid-State Circuits Conference. Digest of Technical Papers. ISSCC (Cat. No.01CH37177).

[11]  Leon O. Chua,et al.  The simplicial neural cell and its mixed-signal circuit implementation: an efficient neural-network architecture for intelligent signal processing in portable multimedia applications , 2002, IEEE Trans. Neural Networks.

[12]  Leon O. Chua,et al.  A robust and efficient universal CNN cell circuit using simplicial neuro-fuzzy inferences for fast image processing , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[13]  Alfredo C. Desages,et al.  Orthonormal high-level canonical PWL functions with applications to model reduction , 2000 .

[14]  Leon O. Chua,et al.  CNN: A Vision of Complexity , 1997 .

[15]  Leon O. Chua,et al.  UNIVERSAL CNN CELLS , 1999 .

[16]  Ernest S. Kuh,et al.  Solving nonlinear resistive networks using piecewise-linear analysis and simplicial subdivision , 1977 .