We address the question of when a network can be expected to generalize from m random training examples chosen from some arbitrary probability distribution, assuming that future test examples are drawn from the same distribution. Among our results are the following bounds on appropriate sample vs, network size. Assume 0 < E 5 1/8. We show that if m 2 0($209!) random examples can be loaded on a ...

In this paper, we propose a method for predicting functional properties of soil samples from a number of measurable spatial and spectral features of those samples. Our method is based on Savitzky-Golay filter for preprocessing and a relatively recent evolution of single hiddenlayer feed-forward network (SLFN) learning technique called extreme learning machine (ELM) for prediction. We tested our...

In this paper we study families of generalized geometric sequences formed by applying a feedforward function to certain sums of decimated m-sequences with elements in a finite field. We compute their correlation functions, which for certain families turn out to be close to the square root of the period. The size of these families equals their period. We also show that in the binary case the lin...

STDP strengthens/weakens synapses driving late/early-spiking cells [Laurent07]

Robert c. Eaton E. P. O. Biology University of Colorado Boulder, Co. 80309 We provide a computational description of the function of the Mauthner system. This is the brainstem circuit which initiates faststart escapes in teleost fish in response to sounds. Our simulations, using back propagation in a realistically constrained feedforward network, have generated hypotheses which are directly int...