Highlights• Deep learning networks are applied to stock market analysis and prediction.• A comprehensive analysis with different data representation methods is offered.• Five-minute intraday data from the Korean KOSPI stock market is used.• The network applied to residuals of autoregressive model improves prediction.• Covariance estimation for market structure analysis is improved with the network. AbstractWe offer a systematic analysis of the use of deep learning networks for stock market analysis and prediction. Its ability to extract features from a large set of raw data without relying on prior knowledge of predictors makes deep learning potentially attractive for stock market prediction at high frequencies. Deep learning algorithms vary considerably in the choice of network structure, activation function, and other model parameters, and their performance is known to depend heavily on the method of data representation. Our study attempts to provides a comprehensive and objective assessment of both the advantages and drawbacks of deep learning algorithms for stock market analysis and prediction. Using high-frequency intraday stock returns as input data, we examine the effects of three unsupervised feature extraction methods-principal component analysis, autoencoder, and the restricted Boltzmann machine-on the network's overall ability to predict future market behavior. Empirical results suggest that deep neural networks can extract additional information from the residuals of the autoregressive model and improve prediction performance; the same cannot be said when the autoregressive model is applied to the residuals of the network. Covariance estimation is also noticeably improved when the predictive network is applied to covariance-based market structure analysis. Our study offers practical insights and potentially useful directions for further investigation into how deep learning networks can be effectively used for stock market analysis and prediction.

In this article we develop a mathematical theory for optimizing the kinematic dexterity of robotic mechanisms and obtain a collection of analytical tools for robot design. The performance criteria we consider are workspace volume and dexterity; by the latter we mean the ability to move and apply forces in arbitrary directions as easily as possible. Clearly, dexterity and workspace volume are intrinsic to a mechanism, so that any mathematical formulation of these properties must necessarily be independent of the particular coordinate representation of the kinematics. By regarding the forward kinematics of a mechanism as defining a mapping between Riemannian manifolds, we apply the coordinate-free language of differential geometry to define natural measures of kinematic dexterity and workspace volume. This approach takes into account the geometric and topolog ical structures of the joint and workspaces. We show that the functional associated with harmonic mapping theory provides a natural measure of the kinematic dexterity of a mechan ism. Optimal designs among the basic classes of mechanisms are determined as extrema of this measure. We also examine the qualitative connections between kinematic dexterity and workspace volume.

We propose a geometric method for visual tracking, in which the 2-D affine motion of a given object template is estimated in a video sequence by means of coordinateinvariant particle filtering on the 2-D affine group Aff(2). Tracking performance is further enhanced through a geometrically defined optimal importance function, obtained explicitly via Taylor expansion of a principal component analysis based measurement function on Aff (2). The efficiency of our approach to tracking is demonstrated via comparative experiments. 991 978-1-4244-3991-1/09/$25.00 ©2009 IEEE

SUMMARYThe Tangent Bundle Rapidly Exploring Random Tree (TB-RRT) is an algorithm for planning robot motions on curved configuration space manifolds, in which the key idea is to construct random trees not on the manifold itself, but on tangent bundle approximations to the manifold. Curvature-based methods are developed for constructing tangent bundle approximations, and procedures for random node generation and bidirectional tree extension are developed that significantly reduce the number of projections to the manifold. Extensive numerical experiments for a wide range of planning problems demonstrate the computational advantages of the TB-RRT algorithm over existing constrained path planning algorithms.