Some Complexity Results for Perceptron Networks
نویسنده
چکیده
The loading problem is the problem to decide if a neural architecture can map a training set correctly with an appropriate choice of the weights. The following results will be shown: The loading problem is NP-complete for any feedforward perceptron architecture with at least two neurons in the rst hidden layer and varying input dimension. Further, it is NP-complete if the input dimension is xed, but if the number of neurons can vary in an architecture with at least two hidden layers. Finally, for a recurrent perceptron network with xed architecture and xed input dimension, but arbitrary input length the loading problem is solvable in polynomial time.
منابع مشابه
Deepest Neural Networks
This paper shows that a long chain of perceptrons (that is, a multilayer perceptron, or MLP, with many hidden layers of width one) can be a universal classifier. The classification procedure is not necessarily computationally efficient, but the technique throws some light on the kind of computations possible with narrow and deep MLPs.
متن کاملA Pilot Sampling Method for Multi-layer Perceptrons
As the size of samples grows, the accuracy of trained multi-layer perceptrons grows with some improvement in error rates. But we cannot use larger and larger samples, because computational complexity to train the multi-layer perceptrons becomes enormous and data overfitting problem can happen. This paper suggests an effective approach in determining a proper sample size for multi-layer perceptr...
متن کاملAn Automated MR Image Segmentation System Using Multi-layer Perceptron Neural Network
Background: Brain tissue segmentation for delineation of 3D anatomical structures from magnetic resonance (MR) images can be used for neuro-degenerative disorders, characterizing morphological differences between subjects based on volumetric analysis of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF), but only if the obtained segmentation results are correct. Due to image arti...
متن کاملA Complexity-Based Approach in Image Compression using Neural Networks
In this paper we present an adaptive method for image compression that is based on complexity level of the image. The basic compressor/de-compressor structure of this method is a multilayer perceptron artificial neural network. In adaptive approach different Back-Propagation artificial neural networks are used as compressor and de-compressor and this is done by dividing the image into blocks, c...
متن کاملDISTURBANCE REJECTION IN NONLINEAR SYSTEMS USING NEURO-FUZZY MODEL
The problem of disturbance rejection in the control of nonlinear systems with additive disturbance generated by some unforced nonlinear systems, was formulated and solved by {itshape Mukhopadhyay} and {itshape Narendra}, they applied the idea of increasing the order of the system, using neural networks the model of multilayer perceptron on several systems of varying complexity, so the objective...
متن کامل