Exponential lower bounds on the size of constant-depth threshold circuits with small energy complexity

A complexity measure for threshold circuits, called the energy complexity, has been proposed to measure an amount of energy consumed during computation in the brain. Biological neurons need more energy to transmit a ''spike'' than not to transmit one, and hence the energy complexity of a threshold circuit is defined as the number of gates in the circuit that output ''1'' during computation. Since the firing activity of neurons in the brain is quite sparse, the following question arises: what Boolean functions can or cannot be computed by threshold circuits with small energy complexity. In the paper, we partially answer the question, that is, we show that there exists a trade-off among three complexity measures of threshold circuits: the energy complexity, size, and depth. The trade-off implies an exponential lower bound on the size of constant-depth threshold circuits with small energy complexity for a large class of Boolean functions.

[1]  John H. Reif,et al.  Energy complexity of optical computations , 1990, Proceedings of the Second IEEE Symposium on Parallel and Distributed Processing 1990.

[2]  Peter Földiák,et al.  SPARSE CODING IN THE PRIMATE CORTEX , 2002 .

[3]  Akira Maruoka,et al.  On the Complexity of Depth-2 Circuits with Threshold Gates , 2005, MFCS.

[4]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[5]  Ian Parberry,et al.  Circuit complexity and neural networks , 1994 .

[6]  Eiji Takimoto,et al.  An Exponential Lower Bound on the Size of Constant-Depth Threshold Circuits with Small Energy Complexity , 2007, Twenty-Second Annual IEEE Conference on Computational Complexity (CCC'07).

[7]  David J. Field,et al.  How Close Are We to Understanding V1? , 2005, Neural Computation.

[8]  P. Lennie.  The Cost of Cortical Computation , 2003, Current Biology.

[9]  Pavel Pudlák,et al.  Threshold circuits of bounded depth , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[10]  Johan Håstad,et al.  On the power of small-depth threshold circuits , 1991, computational complexity.

[11]  Eyal Kushilevitz,et al.  Communication Complexity , 1997, Adv. Comput..

[12]  Jürgen Forster.  A linear lower bound on the unbounded error probabilistic communication complexity , 2002, J. Comput. Syst. Sci..

[13]  Gloria Kissin.  Upper and lower bounds on switching energy in VLSI , 1991, JACM.

[14]  Alexander A. Razborov,et al.  n^Omega(log n) Lower Bounds on the Size of Depth-3 Threshold Circuits with AND Gates at the Bottom , 1993, Information Processing Letters.

[15]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[16]  Wolfgang Maass,et al.  On the Computational Power of Threshold Circuits with Sparse Activity , 2006, Neural Computation.

[17]  B. Sakmann,et al.  In vivo, low-resistance, whole-cell recordings from neurons in the anaesthetized and awake mammalian brain , 2002, Pflügers Archiv.

[18]  N. Nisan.  The communication complexity of threshold gates , 1993 .