We present a McCulloch-Pitts neural net to recognize even linear languages. The language class is studied in order to define the net topology. Finally, the equivalence between the language class and the languages recognized by the net is proved.

This paper presents a sample of what evolved neural net circuit modules using the socalled ”CoDi-1Bit” neural net model can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot ”Robokoneko”. It looks as though the figure is more likely to be 4...

Retrieved profiles of temperature, water vapor, and cloud liquid water are obtained through neural net inversions of the brightness temperatures, where the neural net is trained using radiosonde soundings and corresponding forward modeled brightness temperatures. An observation operator has also been developed for the direct assimilation of the measured brightness temperatures, using the forwar...

This paper describes the application of neural nets to the management of structural safety at ISMES. A neural net was developed to deal with monitoring data evaluation, in order to perform heuristic interpretation of the data. The net achieves the same results of symbolic processors previously used, but with reduced development and tuning effort.

We investigate the construction, training and application of a neural net for assessing element shape quality of practical unstructured grids arising in mesh generation, adaptive refinement and moving grid applications. Results of numerical experiments are included to validate the process and demonstrate performance of the neural net for both triangulations in 2D and tetrahedral tessellation in...

How Neural Nets Work Alan Lapedes Robert Farber Theoretical Division Los Alamos National Laboratory Los Alamos, NM 87545 There is presently great interest in the abilities of neural networks to mimic "qualitative reasoning" by manipulating neural incodings of symbols. Less work has been performed on using neural networks to process floating point numbers and it is sometimes stated that neural n...

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a single hidden layer. The transformations of both deep rectifier nets and deep...

It has been known for quite a while that the Vapnik-Chervonenkis dimension (VC-dimension) of a feedforward neural net with linear threshold gates is at most O(w . log w), where w is the total number of weights in the neural net. We show in this paper that this bound is in fact asymptotically optimal. More precisely, we exhibit for any depth d 2 3 a large class of feedforward neural nets of dept...

Spiking Neural P (SN P) system characterizes the movement of spikes among the neurons. Spikes have a similarity with tokens in Petri net where tokens (like spikes) are moved through net according to specific rules. This paper proposes the concept of spiking Petri nets, which are isomorphic to spiking neural P systems. It also gives algorithms to construct spiking Petri net for SN P system and v...

In modern day pattern recognition, neural nets are used extensively. General use of a feedforward neural net consists of a training phase followed by a classi cation phase. Classication of an unknown test vector is very fast and only consists of the propagation of the test vector through the neural net. Training involves an optimization procedure and is very time consuming since a feasible loca...