An Overview of Machine Learning
Learning is a many-faceted phenomenon. Learning processes include the acquisition of new declarative knowledge, the development of motor and cognitive skills through instruction or practice, the organization of new knowledge into general, effective repres
- PDF / 1,484,603 Bytes
- 21 Pages / 481.89 x 691.654 pts Page_size
- 88 Downloads / 243 Views
Jaime G. Carbonell Carnegie-Mellon University Ryszard S. Michalski University of Illinois at Urbana-Champaign Tom M. Mitchell Rutgers University 1.1 INTRODUCTION
Learning is a many-faceted phenomenon. Learning processes include the acquisition of new declarative knowledge, the development of motor and cognitive skills through instruction or practice, the organization of new knowledge into general, effective representations, and the discovery of new facts and theories through observation and experimentation. Since the inception of the computer era, researchers have been striving to implant such capabilities in computers. Solving this problem has been, and remains, a most challenging and fascinating long-range goal in artificial intelligence .(AI). The study and computer modeling of learning processes in their multiple manifestations constitutes the subject matter of machine learning. 1.2 THE OBJECTIVES OF MACHINE LEARNING
At present, the field of machine learning is organized around three primary research foci: • Task-Oriented Studies-the development and analysis of learning systems to improve performance in a predetermined set of tasks (also known as the "engineering approach") R. S. Michalski et al. (eds.), Machine Learning © Springer-Verlag Berlin Heidelberg 1983
4
CHAPTER 1: AN OVERVIEW OF MACHINE LEARNING
• Cognitive Simulation-the investigation and computer simulation of human learning processes • Theoretical Analysis-the theoretical exploration of the space of possible learning methods and algorithms independent of application domain
Although many research efforts strive primarily towards one of these objectives, progress towards one objective often leads to progress towards another. For instance, in order to investigate the space of possible learning methods, a reasonable starting point may be to consider the only known example of robust learning behavior, namely humans (and perhaps other biological systems). Similarly, psychological investigations of human learning may be helped by theoretical analysis that may suggest various plausible learning models. The need to acquire a particular form of knowledge in some task-oriented study may itself spawn new theoretical analysis or pose the question: "How do humans acquire this specific skill (or knowledge)?" This trichotomy of mutually challenging and supportive objectives is a reflection of the entire field of artificial intelligence, where expert systems research, cognitive simulation, and theoretical studies provide cross-fertilization of problems and ideas. 1.2.1 Applied Learning Systems: A Practical Necessity
At present, instructing a computer or a computer-controlled robot to perform a task requires one to define a complete and correct algorithm for that task, and then laboriously program the algorithm into a computer. These activities typically involve a tedious and time-consuming effort by specially trained personnel. Present-day computer systems cannot truly learn to perform a task through examples or by analogy to a similar, previously-solved ta
Data Loading...
