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

http://www.nt.ntnu.no/users/skoge/prost/proceedings/ifac11-proceedings/data/html/papers/1948.pdf

Robust Feedforward control for a Drop-on-Demand Inkjet Printhead

Search missions require motion planning and navigation methods for information gathering that continuously replan based on new observations of the robot's surroundings. Current methods for information gathering, such as Monte Carlo Tree Search, are capable of reasoning over long horizons, but they are computationally expensive. An alternative for fast online execution is to train, offline, an information gathering policy, which indirectly reasons about the information value of new observations. However, these policies lack safety guarantees and do not account for the robot dynamics. To overcome these limitations we train an information-aware policy via deep reinforcement learning, that guides a receding-horizon trajectory optimization planner. In particular, the policy continuously recommends a reference viewpoint to the local planner, such that the resulting dynamically feasible and collision-free trajectories lead to observations that maximize the information gain and reduce the uncertainty about the environment. In simulation tests in previously unseen environments, our method consistently outperforms greedy next-best-view policies and achieves competitive performance compared to Monte Carlo Tree Search, in terms of information gains and coverage time, with a reduction in execution time by three orders of magnitude.

Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning

Policy Derivation Methods for Critic-Only Reinforcement Learning in Continuous Action Spaces

Interpretability aspects of fuzzy models have received quite some attention in recent years and may be obtained by using transparent rule-structures and well characterized fuzzy membership functions. Moreover, model compactness is important for the interpretability and is related to the number of rules and fuzzy sets. Besides these two criteria, the model accuracy should always be taken into account. In this way, several criteria appear in fuzzy modeling and then multiobjective evolutionary algorithms are a suitable, because these are able to capture several non-dominated solutions in a single run of the algorithm. For fuzzy modeling, we describe two multi-objective evolutionary algorithms that consider all three objectives. Differences between both algorithms arise in the fuzzy sets considered, trapezoidal and gaussian respectively. The algorithms apply an accuracy criterium and a transparency criterium, based on fuzzy set similarity, while compactness is achieved by a specific technique, incorporated ad hoc within the evolutionary algorithms. Finally, we propose a decision process to find the most satisfactory non-dominated solution. Results are shown for three approximation problems that were studied before by others authors.

Accurate, transparent and compact fuzzy models by multi-objective evolutionary algorithms

The two main directions to improve traffic flows in networks involve changing the network topology and introducing new traffic control measures. In this paper, we consider a co-design approach to apply these two methods jointly to improve the interaction between different methods and to get a better overall performance. We aim at finding the optimal network topology and the optimal parameters of traffic control laws at the same time by solving a co-optimization problem. However, such an optimization problem is usually highly non-linear and non-convex, and it possibly involves a mixed-integer form. Therefore, we discuss four different solution frameworks that can be used for solving the co-optimization problem, according to different requirements on the computational complexity and speed. A simulation-based study is implemented on the Singapore freeway network to illustrate the co-design approach and to compare the four different solution frameworks.

Robert Babuska

Papers

Robust Feedforward control for a Drop-on-Demand Inkjet Printhead

Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning

Policy Derivation Methods for Critic-Only Reinforcement Learning in Continuous Action Spaces

Accurate, transparent and compact fuzzy models by multi-objective evolutionary algorithms

Co-design of traffic network topology and control measures