Optimization of circuits using a constructive learning algorithm

The paper presents an application of a constructive learning algorithm to optimization of circuits. For a given Boolean function f. a fresh constructive learning algorithm builds circuits belonging to the smallest F{sub n,m} class of functions (n inputs and having m groups of ones in their truth table). The constructive proofs, which show how arbitrary Boolean functions can be implemented by this algorithm, are shortly enumerated An interesting aspect is that the algorithm can be used for generating both classical Boolean circuits and threshold gate circuits (i.e. analogue inputs and digital outputs), or a mixture of them, thus taking advantage of mixed analogue/digital technologies. One illustrative example is detailed The size and the area of the different circuits are compared (special cost functions can be used to closer estimate the area and the delay of VLSI implementations). Conclusions and further directions of research are ending the paper.

[1]  Robert C. Williamson.  e-Entropy and the Complexity of Feedforward Neural Networks , 1990, NIPS 1990.

[2]  Valeriu Beiu,et al.  Tight Bounds on the Size of Neural Networks for Classification Problems , 1997, IWANN.

[3]  Albert A. Mullin,et al.  Review: O. B. Lupanov, On a Method of Circuit Synthesis , 1970 .

[4]  Robert C. Minnick,et al.  Linear-Input Logic , 1961, IRE Trans. Electron. Comput..

[5]  Rudy Lauwereins,et al.  Learning From Examples and VSLI Implementation of Neural Networks , 1994 .

[6]  Michael E. Saks,et al.  On threshold circuits for parity , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[7]  Roman Smolensky,et al.  Algebraic methods in the theory of lower bounds for Boolean circuit complexity , 1987, STOC.

[8]  N. P. Red’kin.  Synthesis of threshold circuits for certain classes of Boolean functions , 1970 .

[9]  Joos Vandewalle,et al.  Area-Time Performances of Some Neural Computations , 1994 .

[10]  Valeriu Beiu,et al.  Direct synthesis of neural networks , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[11]  Byoung-Tak Zhang,et al.  Genetic Programming of Minimal Neural Nets Using Occam's Razor , 1993, ICGA.

[12]  V. Beiu,et al.  Constant fan-in digital neural networks are VLSI-optimal , 1995 .

[13]  Rudy Lauwereins,et al.  Comparison and Threshold Gate Decomposition , 1993 .

[14]  Joseph W. Goodman,et al.  On the power of neural networks for solving hard problems , 1990, J. Complex..

[15]  Dan Hammerstrom,et al.  The Connectivity Analysis of Simple Association - or- How Many Connections Do You Need! , 1988 .

[16]  S. Drăghici,et al.  Limited weights neural networks: Very tight entropy based bounds , 1997 .

[17]  Robert O. Winder,et al.  Threshold logic , 1971, IEEE Spectrum.

[18]  Ishwar K. Sethi,et al.  On the Possibilities of the Limited Precision Weights Neural Networks in Classification Problems , 1997, IWANN.