Machine learning. Modelling of learning by machines
The book contains various contributions to the field of machine learning ranging from the area of computer science to the field of cognitive science and psychology. Various machine learning methodologies are applied: explanation-based learning, similarity-based learning, case- based reasoning, learning by analogy and connectionist principles. The book contains nine contributions, with topics treated such as visual recognition and visual learning by means of neural networks (\textit{Meyering} and \textit{Ritter}), planning tasks and learning procedures underlying autonomous robot control and robot motion in a room with obstacles (\textit{Spandl}), or the efficiency of domain-specific heuristics with respect to fault-diagnosis in technical systems (\textit{Althoff}). Several papers consider learning problems in the task domain of programming and the acquisition of programming competence and strategies. One of these articles presents a model of learning processes and appropriate support by a tutoring system that dynamically adapts to the student's capabilities based on a continuously updated internal model of the learner (\textit{Schröder} and \textit{Möbius}). Concrete learning processes in the course of acquiring the knowledge and procedural expertise of a programming language are described with respect to program solutions of recursive problems and the prominent role of recursion schemata in this process (\textit{Goebel} and \textit{Vorberg}), the use of programming schemata for learning horn clauses in the course of acquiring knowledge of the programming language Prolog (\textit{Tausend}), a case- based tutoring system for learning the programming language Lisp (\textit{Weber}), the cognitive processes of novices underlying the learning of the Lisp programming language where, in particular, the effects of extracting knowledge from text sources and programming examples for the adequate solution of programming problems are examined (\textit{Bergmann}, \textit{Boschert} and \textit{Schmalhofer}). Finally, the processes underlying the solution of mathematical problems, i.e., understanding the textual form of an exercise, transforming it into an episodic problem model, finding the mathematical problem solution, and verbally expressing the answer to the original problem are considered in the framework of cognitive modelling (\textit{Reusser}).
- Self-organization of markets: An example of a computational approach
- Modelling on human intelligence a machine learning system
- Machine learning versus statistical modeling
- scientific article; zbMATH DE number 52339 (Why is no real title available?)
- scientific article; zbMATH DE number 1523025 (Why is no real title available?)
- Computational models of learning
- scientific article; zbMATH DE number 4001516 (Why is no real title available?)
- Deep reinforcement trading with predictable returns
This page was built for publication: Machine learning. Modelling of learning by machines
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4023681)
