Using Backpropagation with Temporal Windows
نویسنده
چکیده
Computing the inverse dynamics of a robot ann is an active area of research in the control literature. We hope to learn the inverse dynamics by training a neural network on the measured response of a physical ann. The input to the network is a temporal window of measured positions; output is a vector of torques. We train the network on data measured from the first two joints of the CMU Direct-Drive Arm II as it moves through a randomly-generated sample of "pick-and-place" trajectories. We then test generalization with a new trajectory and compare its output with the torque measured at the physical arm. The network is shown to generalize with a root mean square error/standard deviation (RMSS) of 0.10. We interpreted the weights of the network in tenns of the velocity and acceleration filters used in conventional control theory.
منابع مشابه
Efficient Methods for Dealing with Missing Data in Supervised Learning
Subutai Ahmad Interval Research Corporation 1801-C Page Mill R<;l. Palo Alto, CA 94304 We present efficient algorithms for dealing with the problem of missing inputs (incomplete feature vectors) during training and recall. Our approach is based on the approximation of the input data distribution using Parzen windows. For recall, we obtain closed form solutions for arbitrary feedforward networks...
متن کاملEecient Methods for Dealing with Missing Data in Supervised Learning
We present eecient algorithms for dealing with the problem of missing inputs (incomplete feature vectors) during training and recall. Our approach is based on the approximation of the input data distribution using Parzen windows. For recall, we obtain closed form solutions for arbitrary feedforward networks. For training, we show how the backpropagation step for an incomplete pattern can be app...
متن کاملAn Investigation of the Gradient Descent Process in Neural Networks
Usually gradient descent is merely a way to find a minimum, abandoned if a more efficient technique is available. Here we investigate the detailed properties of the gradient descent process, and the related topics of how gradients can be computed, what the limitations on gradient descent are, and how the second-order information that governs the dynamics of gradient descent can be probed. To de...
متن کاملSpectral Estimation of Printed Colors Using a Scanner, Conventional Color Filters and applying backpropagation Neural Network
Reconstruction the spectral data of color samples using conventional color devices such as a digital camera or scanner is always of interest. Nowadays, multispectral imaging has introduced a feasible method to estimate the spectral reflectance of the images utilizing more than three-channel imaging. The goal of this study is to spectrally characterize a color scanner using a set of conventional...
متن کاملA New Compression Technique Using an Artificial Neural Network
In this paper, we present a direct solution method based neural network for image compression. The proposed technique includes steps to break down large images into smaller windows and eliminate redundant information. Furthermore, the technique employs a neural network trained by a non-iterative, direct solution method. An error backpropagation algorithm is also used to train the neural network...
متن کامل