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

Over the past decades, machine learning techniques, such as supervised learning, reinforcement learning, and unsupervised learning, have been increasingly used in the control engineering community. Various learning algorithms have been developed to achieve autonomous operation and intelligent decision making for many complex and challenging control problems. One of such problems is bipedal walking robot control. Although still in their early stages, learning techniques have demonstrated promising potential to build adaptive control systems for bipedal robots. This paper gives a review of recent advances on the state-of-the-art learning algorithms and their applications to bipedal robot control. The effects and limitations of different learning techniques are discussed through a representative selection of examples from the literature. Guidelines for future research on learning control of bipedal robots are provided in the end.

Machine Learning Algorithms in Bipedal Robot Control

This paper introduces an algorithm for direct search of control policies in continuous-state discrete-action Markov decision processes. The algorithm looks for the best closed-loop policy that can be represented using a given number of basis functions (BFs), where a discrete action is assigned to each BF. The type of the BFs and their number are specified in advance and determine the complexity of the representation. Considerable flexibility is achieved by optimizing the locations and shapes of the BFs, together with the action assignments. The optimization is carried out with the cross-entropy method and evaluates the policies by their empirical return from a representative set of initial states. The return for each representative state is estimated using Monte Carlo simulations. The resulting algorithm for cross-entropy policy search with adaptive BFs is extensively evaluated in problems with two to six state variables, for which it reliably obtains good policies with only a small number of BFs. In these experiments, cross-entropy policy search requires vastly fewer BFs than value-function techniques with equidistant BFs, and outperforms policy search with a competing optimization algorithm called DIRECT.

/pdf/cross-entropy-optimization-of-control-policies-with-adaptive-24an7clh4f.pdf

Cross-Entropy Optimization of Control Policies With Adaptive Basis Functions

Comments on recent publications about the use of orthogonal transforms to order and select rules in a fuzzy rule base. The techniques are well-known from linear algebra, and we comment on their usefulness in fuzzy modeling. The application of rank-revealing methods based on singular value decomposition (SVD) to rule reduction gives rather conservative results. They are essentially subset selection methods, and we show that such methods do not produce an "importance ordering", contrary to what has been stated in the literature. The orthogonal least-squares (OLS) method, which evaluates the contribution of the rules to the output, is more attractive for systems modeling. However, it has been shown to sometimes assign high importance to rules that are correlated in the premise. This hampers the generalization capabilities of the resulting model. We discuss the performance of rank-revealing reduction methods and advocate the use of a less complex method based on the pivoted QR decomposition. Further, we show how detection of redundant rules can be introduced in OLS by a simple extension of the algorithm. The methods are applied to a problem known from the literature and compared to results reported by other researchers.

/pdf/rule-base-reduction-some-comments-on-the-use-of-orthogonal-3qva4zvkog.pdf

Rule base reduction: some comments on the use of orthogonal transforms

Modern processes in industry are characterized by nonlinear and time-varying behavior. Nonlinear system identification is becoming an important tool which can be used to improve control performance and achieve robust fault-tolerant behavior. Among the different nonlinear identification techniques, methods based on neuro-fuzzy models are gradually becoming established not only in the academia but also in industrial applications. Neurofuzzy modeling can be regarded as a gray-box technique on the boundary between neural networks and qualitative fuzzy models. The tools for building neuro-fuzzy models are based on combinations of algorithms from the fields of neural networks, pattern recognition and regression analysis. This chapter addresses the use of neuro-fuzzy models in system identification.

Neuro-fuzzy methods for modeling and identification

This paper presents a method for deriving a linguistic fuzzy model from an already identified fuzzy linear model. The approach is based on the novel concept of complementary fuzzy partition which is derived from the partition of a fuzzy linear model. It combines a well established identification method for fuzzy linear models with a good semantic interpretation capabilities of linguistic fuzzy models. The method is applied to the identification of a linguistic fuzzy model of a highly nonlinear process. It is shown that along with the semantic meaning the global numerical accuracy is also improved, compared to the original fuzzy linear model. >

https://ieeexplore.ieee.org/iel2/3225/9176/00409790.pdf

Robert Babuska

Papers

Machine Learning Algorithms in Bipedal Robot Control

Cross-Entropy Optimization of Control Policies With Adaptive Basis Functions

Rule base reduction: some comments on the use of orthogonal transforms

Neuro-fuzzy methods for modeling and identification

A new identification method for linguistic fuzzy models