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

Supervised model-based self-tuning control of fermentation processes is addressed. The diversity, nonlinearity and time-varying nature of these processes make their control a challenging task. Conventional linear (PID) controllers with fixed parameters cannot meet the increasing performance requirements over the whole operating range. In the approach pursued in this research, a local linear model is identified at the current working point by using a limited amount input--output data obtained through an identification experiment. A linear controller is then tuned on the basis of this model. To minimize the intervention into the process operation, this tuning procedure is only initiated if the performance of the current controller deteriorates. To this end, a supervisory expert system is designed whose tasks are to monitor the process performance, design an appropriate identification experiment, validate the obtained model and tune the controller. The supervisory system is based on a combination of a state automaton with a rule-based fuzzy inference system. Experimental results have demonstrated the feasibility of this approach.

Fuzzy supervision of adaptive control with an application to bioreactors

In this paper, the authors introduce a co-optimization approach to jointly optimize the traffic network topology traffic controllers on the network. Since the network topology design has a long-term goal, while the traffic control is usually based on a minute-to-minute basis traffic situation, the authors uses a so-called parameterized traffic control method to bring them to the same time scale. They applied the proposed co-optimization approach in a simulation-based case study, and compared it with a pure topology design and an iterative optimization method. The results show that this method can improve the interaction between topology design and traffic control design, and result in a better overall performance.

Co-Optimization of Topology Design and Parameterized Control in a Traffic Network

Several stable adaptive fuzzy control schemes based on feedback linearization and Lyapunov synthesis were proposed in the literature. However, most of such controllers have been only tested on relatively simple simulations examples, in which the effects of noise, uncertainties, computational times and other fundamental problems related to hardware implementation are neglected. In this paper, we study and compare direct and indirect adaptive control schemes by means of an experimental benchmark (two coupled DC machines). For the indirect schemes, we consider both the standard adaptive laws based on tracking error and composite adaptive laws based on tracking and prediction error. The goal of this work is to gain insight in the benefits and drawbacks of the different variants of adaptive fuzzy controllers and to evaluate their potential for practical applications

Evaluation of adaptive fuzzy controllers: a real-world experiment

Deep neural networks designed for vision tasks are often prone to failure when they encounter environmental conditions not covered by the training data. Single-modal strategies are insufficient when the sensor fails to acquire information due to malfunction or its design limitations. Multi-sensor configurations are known to provide redundancy, increase reliability, and are crucial in achieving robustness against asymmetric sensor failures. To address the issue of changing lighting conditions and asymmetric sensor degradation in object detection, we develop a multi-modal 2D object detector, and propose deterministic and stochastic sensor-aware feature fusion strategies. The proposed fusion mechanisms are driven by the estimated sensor measurement reliability values/weights. Reliable object detection in harsh lighting conditions is essential for applications such as self-driving vehicles and human-robot interaction. We also propose a new "r-blended" hybrid depth modality for RGB-D sensors. Through extensive experimentation, we show that the proposed strategies outperform the existing state-of-the-art methods on the FLIR-Thermal dataset, and obtain promising results on the SUNRGB-D dataset. We additionally record a new RGB-Infra indoor dataset, namely L515-Indoors, and demonstrate that the proposed object detection methodologies are highly effective for a variety of lighting conditions.

GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection.

Legged robots are intrinsically nonlinear hybrid dynamic systems due to the intermittent contact of the feet with the ground. For optimal performance, in the sense of maximizing speed or energy consumption, different motion control affects the stance from the swing leg during a stride. Designing such controllers, however, can be a daunting task when there is a lack of knowledge about the exact operating conditions, i.e., the surface on which the robot walks or runs. To address this problem, we present a model-free learning controller making use of a supervised machine learning method called Local Linear Regression. This method allows the controller to online adjust its controller parameters as a function of the state. We demonstrate this approach on a tunable stiffness and damping controller for a quadrupedal legged robot. The controller learns to compensate for friction and other nonlinear effects encountered while walking in an average sense, without the use of explicit models. Experimental results with the robot walking on a treadmill are presented.

Robert Babuska

Papers

Fuzzy supervision of adaptive control with an application to bioreactors

Co-Optimization of Topology Design and Parameterized Control in a Traffic Network

Evaluation of adaptive fuzzy controllers: a real-world experiment

GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection.

Stiffness and damping scheduling for legged locomotion