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

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

A review of shape memory alloy research, applications and opportunities

Survey: Reservoir computing approaches to recurrent neural network training

Reference architecture for holonic manufacturing systems: PROSA

A 5 mm diameter tri-axial force sensor has been developed for minimally invasive robotic surgery. To define the required force range and resolution, a needle driver has been equipped with strain gauges. In vivo tests with different types of needles and tissue show that the required force range and resolution are, respectively, 2.5 N and 0.01 N. The new sensor is based on a flexible titanium structure of which the deformations are measured through reflective measurements with three optical fibres. It has a range of 2.5 N in axial direction and 1.7 N in radial direction.

A micro-optical force sensor for force feedback during minimally invasive robotic surgery

Two main challenges in using a pneumatic artificial muscle (PAM) actuator are the nonlinearity of pneumatic system and the nonlinearity of the PAM dynamics. The latter is complicated to characterize. In this paper, a Maxwell-slip model used as a lumped-parametric quasi-static model is proposed to capture the force/length hysteresis of a PAM. The intuitive selection of elements in this model interprets the unclear, but blended contributing causes of the hysteresis very well, which are assumed to originate from the dry friction of the double helix weaving of the PAM braided shell, the friction of the weaving and the bladder, the elasticity of the bladder and/or the deformation of the conical parts of a PAM close to the end caps. The obtained model is simple, but physically meaningful and easy to handle in terms of control.

A New Approach to Modeling Hysteresis in a Pneumatic Artificial Muscle Using The Maxwell-Slip Model

Open Control Systems are the key enabler for the realization of modular and re-configurable manufacturing systems. The large number of special purpose machines and the high level of automation have led to an increasing importance of open control systems based on vendor neutral standards. This paper gives an overview on the past, present and future of Open Controller Architecture. After reflecting on the different criteria, categories and characteristics of open controllers in general, the CNC products in the market are evaluated and an overview on the world-wide research activities in Europe, North America and Japan is given. Subsequently the efforts to harmonize the different results are described in order to establish a common world-wide standard in the future. Due to the “mix-and-match” nature of open controllers concentrated attention must be paid to testing mechanisms in the form of conformance and interoperability tests.

Hendrik Van Brussel

Papers

Reference architecture for holonic manufacturing systems: PROSA

A micro-optical force sensor for force feedback during minimally invasive robotic surgery

A New Approach to Modeling Hysteresis in a Pneumatic Artificial Muscle Using The Maxwell-Slip Model

Open Controller Architecture – Past, Present and Future

Multi-agent coordination and control using stigmergy