A difficult task of a sketch understanding system is that it should always try to balance between the drawing freedom and the complexity of recognition. Most online existing works are based on the assumption that people will not start to draw a new symbol before the last one has been finished. As obviously it is not always the case, we propose in this paper a method which relaxes this constrain...

A recurring theme in theoretical work is that integration over populations of similarly tuned neurons can reduce neural noise. However, there are relatively few demonstrations of an explicit noise reduction mechanism in a neural network. Here we demonstrate that the brainstem of the barn owl includes a stage of processing apparently devoted to increasing the signal-to-noise ratio in the encodin...

Based on MATLAB, a new model-BRF network model is founded to be used in groundwater dynamic simulation and prediction. It is systematically studied about the training sample set, testing sample set, the pretreatment of the original data, neural network construction, training, testing and evaluating the entire process. A favorable result is achieved by applying the model to simulate and predict ...

A work on neural network and fuzzy logic based technique for solving the problem of unit commitment in any electric utility is presented in this paper. The effectiveness of economic dispatch is well understood when the objective is to schedule the committed generators to meet the load, maintain voltages and frequency within prescribed tolerances and minimize operating cost without unduly stress...

We propose novel methods of solving two tasks using Convolutional Neural Networks, firstly the task of generating HDR map of a static scene using differently exposed LDR images of the scene captured using conventional cameras and secondly the task of finding an optimal tone mapping operator that would give a better score on the TMQI metric compared to the existing methods. We quantitatively sho...

This paper presents a method for developing control laws for nonlinear systems based on an optimal control formulation. Due to the nonlinearities of the system, no analytical solution exists. The method proposed here uses the 'black box' structure of a neural network to model a feedback control law. The network is trained with the back-propagation learning method by using examples of optimal co...

An artificial neural network has been trained by the error back-propagation technique to recognise phonemes and words. The speech material was recorded by a male Swedish talker and was labelled by a phonetician. There were 38 output nodes corresponding to Swedish phonemes. Introducing coarticulation information by adding simple recurrency to the net is shown to more effective than expanding the...

This paper presents a vision sensor-based solution to the challenging problem of detecting and following trails in highly unstructured natural environments like forests, rural areas and mountains, using a combination of a deep neural network and dynamic programming. The deep neural network (DNN) concept has recently emerged as a very effective tool for processing vision sensor signals. A patch-...

Neural networks have recently been shown to be a very effective approach to the unconstrained segmentation of speech into phoneme-like units. The neural network is trained to indicate when a short local sequence of feature vectors is associated with a segment boundary, and when it is not. Although this approach delivers state-of-the-art performance, it is prone to over-segmentation at ambiguous...

Dynamic neural networks are often used for nonlinear system identification. This paper presents a novel series-parallel dynamic neural network structure which is suitable for nonlinear system identification. A theoretical proof is given showing that this type of dynamic neural network is able to approximate finite trajectories of nonlinear dynamical systems. Also, this neural network is trained...