Stock price prediction is a challenging task, but machine learning methods have recently been used successfully for this purpose. In this paper, we extract over 270 hand-crafted features (factors) inspired by technical and quantitative analysis and tested their validity on short-term mid-price movement prediction. We focus on a wrapper feature selection method using entropy, least-mean squares, and linear discriminant analysis. We also build a new quantitative feature based on adaptive logistic regression for online learning, which is constantly selected first among the majority of the proposed feature selection methods. This study examines the best combination of features using high frequency limit order book data from Nasdaq Nordic. Our results suggest that sorting methods and classifiers can be used in such a way that one can reach the best performance with a combination of only very few advanced hand-crafted features.

Deep learning models have exhibited superior performance in predictive tasks with the explosively increasing Electronic Health Records (EHR). However, due to the lack of transparency, behaviors of deep learning models are difficult to interpret. Without trustworthiness, deep learning models will not be able to assist in the real-world decision-making process of healthcare issues. We propose a deep learning model based on Bayesian Neural Networks (BNN) to predict uncertainty induced by data noise. The uncertainty is introduced to provide model predictions with an extra level of confidence. Our experiments verify that instances with high uncertainty are harmful to model performance. Moreover, by investigating the distributions of model prediction and uncertainty, we show that it is possible to identify a group of patients for timely intervention, such that decreasing data noise will benefit more on the prediction accuracy for these patients.

Gaussian processes are used in machine learning to learn input-output mappings from observed data. Gaussian process regression is based on imposing a Gaussian process prior on the unknown regressor function and statistically conditioning it on the observed data. In system identification, Gaussian processes are used to form time series prediction models such as non-linear finite-impulse response (NFIR) models as well as non-linear autoregressive (NARX) models. Gaussian process state-space models (GPSS) can be used to learn the dynamic and measurement models for a state-space representation of the input-output data. Temporal and spatio-temporal Gaussian processes can be directly used to form regressor on the data in the time domain. The aim of this article is to briefly outline the main directions in system identification methods using Gaussian processes.

This paper proposes a novel architecture, termed multiscale principle of relevant information (MPRI), to learn discriminative spectral-spatial features for hyperspectral image (HSI) classification. MPRI inherits the merits of the principle of relevant information (PRI) to effectively extract multiscale information embedded in the given data, and also takes advantage of the multilayer structure to learn representations in a coarse-to-fine manner. Specifically, MPRI performs spectral-spatial pixel characterization (using PRI) and feature dimensionality reduction (using regularized linear discriminant analysis) iteratively and successively. Extensive experiments on four benchmark data sets demonstrate that MPRI outperforms existing state-of-the-art HSI classification methods (including deep learning based ones) qualitatively and quantitatively, especially in the scenario of limited training samples. I. INTRODUCTION With the rapid development of hyperspectral imaging techniques, current sensors always have high spectral and spatial resolution [1]. This work was supported in part by the National Natural Science Foundation of China (Grant No. 61502195), and in part by the Office of Naval Research Science of Autonomy (Grant No. N000141812306). Yantao Wei is with School of Educational Information Technology, Central China Normal University, Wuhan 430079, China (email: yantaowei@mail.ccnu.edu.cn).

Experimental data is often affected by uncontrolled variables that make analysis and interpretation difficult. For spatiotemporal systems, this problem is further exacerbated by their intricate dynamics. Modern machine learning methods are well-suited for modeling complex datasets, but to be effective in science, the result needs to be interpretable. We demonstrate an unsupervised learning technique for extracting interpretable physical parameters from noisy spatiotemporal data and for building a transferable model of the system. In particular, we implement a physics-informed architecture based on variational autoencoders that is designed for analyzing systems governed by partial differential equations (PDEs). The architecture is trained end-to-end and extracts latent parameters that parameterize the dynamics of a learned predictive model for the system. To test our method, we train the architecture on simulated data from a variety of PDEs with varying dynamical parameters that act as uncontrolled variables. Specifically, we examine the Kuramoto-Sivashinsky equation with varying viscosity damping parameter, the nonlinear Schr\"odinger equation with varying nonlinearity coefficient, and the convection-diffusion equation with varying diffusion constant and drift velocity. Numerical experiments show that our method can accurately identify relevant parameters and extract them from raw and even noisy spatiotemporal data (tested with roughly 10% added noise). These extracted parameters correlate well (linearly with $R^2>0.95$) with the ground truth physical parameters used to generate the datasets. Our method for discovering interpretable latent parameters in spatiotemporal systems will allow us to better analyze and understand real-world phenomena and datasets, which often have uncontrolled variables that alter the system dynamics and cause varying behaviors that are difficult to disentangle.

In today world of enormous amounts of data, it is very important to extract useful knowledge from it. This can be accomplished by feature subset selection. Feature subset selection is a method of selecting a minimum number of features with the help of which our machine can learn and predict which class a particular data belongs to. We will introduce a new adaptive algorithm called Feature selection Penguin Search optimization algorithm which is a metaheuristic approach. It is adapted from the natural hunting strategy of penguins in which a group of penguins take jumps at random depths and come back and share the status of food availability with other penguins and in this way, the global optimum solution is found. In order to explore the feature subset candidates, the bioinspired approach Penguin Search optimization algorithm generates during the process a trial feature subset and estimates its fitness value by using three different classifiers for each case: Random Forest, Nearest Neighbour and Support Vector Machines. However, we are planning to implement our proposed approach Feature selection Penguin Search optimization algorithm on some well known benchmark datasets collected from the UCI repository and also try to evaluate and compare its classification accuracy with some state of art algorithms.

We introduce Parameterized Exploration (PE), a simple family of methods for model-based tuning of the exploration schedule in sequential decision problems. Unlike common heuristics for exploration, our method accounts for the time horizon of the decision problem as well as the agent's current state of knowledge of the dynamics of the decision problem. We show our method as applied to several common exploration techniques has superior performance relative to un-tuned counterparts in Bernoulli and Gaussian multi-armed bandits, contextual bandits, and a Markov decision process based on a mobile health (mHealth) study. We also examine the effects of the accuracy of the estimated dynamics model on the performance of PE.

This paper describes Motion Planning Networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning problems. MPNet uses neural networks to learn general near-optimal heuristics for path planning in seen and unseen environments. It receives environment information as point-clouds, as well as a robot's initial and desired goal configurations and recursively calls itself to bidirectionally generate connectable paths. In addition to finding directly connectable and near-optimal paths in a single pass, we show that worst-case theoretical guarantees can be proven if we merge this neural network strategy with classical sample-based planners in a hybrid approach while still retaining significant computational and optimality improvements. To learn the MPNet models, we present an active continual learning approach that enables MPNet to learn from streaming data and actively ask for expert demonstrations when needed, drastically reducing data for training. We validate MPNet against gold-standard and state-of-the-art planning methods in a variety of problems from 2D to 7D robot configuration spaces in challenging and cluttered environments, with results showing significant and consistently stronger performance metrics, and motivating neural planning in general as a modern strategy for solving motion planning problems efficiently.

The use of robotics in controlled environments has flourished over the last several decades and training robots to perform tasks using control strategies developed from dynamical models of their hardware have proven very effective. However, in many real-world settings, the uncertainties of the environment, the safety requirements and generalized capabilities that are expected of robots make rigid industrial robots unsuitable. This created great research interest into developing control strategies for flexible robot hardware for which building dynamical models are challenging. In this paper, inspired by the success of deep reinforcement learning (DRL) in other areas, we systematically study the efficacy of policy search methods using DRL in training flexible robots. Our results indicate that DRL is successfully able to learn efficient and robust policies for complex tasks at various degrees of flexibility. We also note that DRL using Deep Deterministic Policy Gradients can be sensitive to the choice of sensors and adding more informative sensors does not necessarily make the task easier to learn.

Since the first use of advanced software in asset-intensive industries more than four decades ago, manufacturers have been on a journey to transform their businesses and create added value for stakeholders. Today, a fresh generation of technologies, fuelled by advances in artificial intelligence based on machine learning, is opening new opportunities to reassess the upper bounds of operational excellence across these sectors. To stay one step ahead of the pack, businesses not only need to understand machine learning complexities but be prepared to act on it and take advantage. After all, the latest machine learning solutions can determine weeks in advance if and when assets are likely to degrade or fail, distinguishing between normal and abnormal equipment and process behavior by recognizing complex data patterns and uncovering the precise signatures of degradation and failure. They can then alert operators and even prescribe solutions to avoid the impending failure, or at least mitigate the consequences.