https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

The purpose of this paper is to provide a comprehensive presentation and interpretation of the Ensemble Kalman Filter (EnKF) and its numerical implementation. The EnKF has a large user group, and numerous publications have discussed applications and theoretical aspects of it. This paper reviews the important results from these studies and also presents new ideas and alternative interpretations which further explain the success of the EnKF. In addition to providing the theoretical framework needed for using the EnKF, there is also a focus on the algorithmic formulation and optimal numerical implementation. A program listing is given for some of the key subroutines. The paper also touches upon specific issues such as the use of nonlinear measurements, in situ profiles of temperature and salinity, and data which are available with high frequency in time. An ensemble based optimal interpolation (EnOI) scheme is presented as a cost-effective approach which may serve as an alternative to the EnKF in some applications. A fairly extensive discussion is devoted to the use of time correlated model errors and the estimation of model bias.

The Ensemble Kalman Filter: Theoretical formulation and practical implementation

Reinforcement learning offers to robotics a framework and set of tools for the design of sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic problems provide both inspiration, impact, and validation for developments in reinforcement learning. The relationship between disciplines has sufficient promise to be likened to that between physics and mathematics. In this article, we attempt to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots. We highlight both key challenges in robot reinforcement learning as well as notable successes. We discuss how contributions tamed the complexity of the domain and study the role of algorithms, representations, and prior knowledge in achieving these successes. As a result, a particular focus of our paper lies on the choice between model-based and model-free as well as between value-function-based and policy-search methods. By analyzing a simple problem in some detail we demonstrate how reinforcement learning approaches may be profitably applied, and we note throughout open questions and the tremendous potential for future research.

/pdf/reinforcement-learning-in-robotics-a-survey-4w4397qx9i.pdf

Reinforcement learning in robotics: A survey

In order to solve the problem of model based control arising from the process model has to be obtained by using small amount and different type of available information, a fuzzy modeling framework has been developed for the utilization of a priori knowledge. The proposed modeling approach transforms the different types of information into the structure of the model (fuzzy rule base), constraints defined on the parameters and variables, dynamic local model or data, and steady-state data or model. This modeling step is followed by an optimization procedure based on these transformed information. The paper describes one element of this framework that was developed to use prior knowledge in constrained adaptation of the rule consequences of Takagi-Sugeno fuzzy models. Experimental results have been obtained for a laboratory setup consisting of two cascaded tanks. It has been shown that by using constrained adaptation, good control performance can be achieved for a nonlinear, time-varying process.

Fuzzy modeling and model based control with use of a priori knowledge

We consider the problem of maximizing the algebraic connectivity of the communication graph in a network of mobile robots by moving them into appropriate positions. We define the Laplacian of the graph as dependent on the pairwise distance between the robots and we approximate the problem as a sequence of Semi-Definite Programs (SDP). We propose a distributed solution consisting of local SDP's which use information only from nearby neighboring robots. We show that the resulting distributed optimization framework leads to feasible subproblems and through its repeated execution, the algebraic connectivity increases monotonically. Moreover, we describe how to adjust the communication load of the robots based on locally computable measures. Numerical simulations show the performance of the algorithm with respect to the centralized solution.

Constrained Distributed Algebraic Connectivity Maximization in Robotic Networks

Fine-tuning Deep RL with Gradient-Free Optimization

Using a priori knowledge in fuzzy model identification

This paper describes a fuzzy decision support system (DSS) for the control of a detergent production process. The application has been carried out at a real-world, large-scale industrial production plant in the Netherlands, where a large variety of powder-based detergents for industrial users are produced in a spray drying process. The system consists of several fuzzy rule bases that model the control actions of experienced process operators in response to different quality deviations of the product. A hierarchical architecture of the fuzzy system is introduced to cope with the complexity. A fuzzy supervisor is used to deal with process constraints and to activate the applicable rule bases when control actions are needed. In this way, a system is obtained that enables the control of the process within stricter quality bounds than those applied by human operators alone. During in-production evaluation, the average improvement in the quality parameters for all product classes was above 30 percent. Copyright © 2001 John Wiley & Sons, Ltd.

Robert Babuska

Papers

Fuzzy modeling and model based control with use of a priori knowledge

Constrained Distributed Algebraic Connectivity Maximization in Robotic Networks

Fine-tuning Deep RL with Gradient-Free Optimization

Using a priori knowledge in fuzzy model identification

Fuzzy decision support for the control of detergent production