论文信息 - Doubly stochastic Poisson processes in artificial neural learning

Doubly stochastic Poisson processes in artificial neural learning

This paper investigates neuron activation statistics in artificial neural networks employing stochastic arithmetic. It is shown that a doubly stochastic Poisson process is an appropriate model for the signals in these circuits.

H. Card

[1] M. Teich,et al. Flat counting distribution for triangularly-modulated poisson process , 1969 .

[2] Brian R. Gaines,et al. Stochastic Computing Systems , 1969 .

[3] Howard C. Card,et al. Stochastic arithmetic implementations of neural networks with in situ learning , 1993, IEEE International Conference on Neural Networks.

[4] Max Stanford Tomlinson,et al. A digital neural network architecture for VLSI , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[5] Alan F. Murray,et al. Pulse-stream VLSI neural networks mixing analog and digital techniques , 1991, IEEE Trans. Neural Networks.

[6] Kimmo Kaski,et al. Pulse-density modulation technique in VLSI implementations of neural network algorithms , 1990 .

[7] Howard C. Card,et al. Parallel Random Number Generation for VLSI Systems Using Cellular Automata , 1989, IEEE Trans. Computers.

[8] H C Card,et al. Photocounting distributions for exponentially decaying sources. , 1979, Optics letters.

[9] Thomas K. Miller,et al. A digital architecture employing stochasticism for the simulation of Hopfield neural nets , 1989 .