"Learning is the act of acquiring new, or modifying and reinforcing existing, knowledge, behaviors, skills, values, or preferences which may lead to a potential change in synthesizing information, depth of the knowledge, attitude or behavior relative to the type and range of experience. The ability to learn is possessed by humans, animals, plants and some machines. Progress over time tends to follow a learning curve. Learning does not happen all at once, but it builds upon and is shaped by previous knowledge. To that end, learning may be viewed as a process, rather than a collection of factual and procedural knowledge. Learning produces changes in the organism and the changes produced are relatively permanent" (Wiki 1).
Learning Definition
Machine learning is the “Self-constructing or self-modifying representations of what is being experienced for possible future use”(Whatwhenhow 8).
Machine Learning Definition
“This paper reports on the PRODIGY architecture, describing its planning and problem solving capabilities and touching upon its multiple learning methods. Learning in PRODIGY occurs at all decision points and integration in PRODIGY is at the knowledge level; the learning and reasoning modules produce mutually interpretable knowledge structures” (PRODIGY 1). “PRODIGY's basic reasoning engine is a general-purpose problem solver and planner that searches for sequences of operators (i.e., plans) to accomplish a set of goals from a specified initial state description” (PRODIGY 3). “To solve a problem, PRODIGY must find a sequence of operators that, if applied to the initial state, produces a final state satisfying the goal expression. The search tree initially starts out as a single node containing the initial state and goal expression. The tree is expanded by repeating the decision and expansion phases” (PRODIGY 5).
“PRODIGY’s general problem solver is combined with several learning modules. The PRODIGY architecture was designed both as a unified testbed for different learning methods and as a general architecture to solve interesting problems in complex task domains” (PRODIGY 12). The seven learning modules are APPRENTICE, EBL, STATIC, ANALOGY, ALPINE, and EXPERIMENT. The proposed dimensions of the architecture, are Generality, Versatility, Rationality, Ability to add new knowledge, Ability to learn, Scalability, Reactivity, Efficiency, and Psychological Validity. These dimensions are the criteria that the proposed architecture meets because of its different components.
PRODIGY: An Integrated Architecture for Planning and Learning
"Learning." Wikipedia. Wikimedia Foundation, n.d. Web. 26 Jan. 2017. <https://en.wikipedia.org/wiki/Learning>.
"Machine Learning (information science)." Whatwhenhow RSS. N.p., n.d. Web. 26 Jan. 2017. <http://what-when-how.com/information-science-and-technology/machine-learning-information-science/>.
Carbonell, Jaime G., Oren Etzioni, Yolanda Gil, Robert Joseph, Craig Knoblock, Steve Minton, and Manuela M. Veloso. "PRODIGY: An Integrated Architecture for Planning and Learning." Research Showcase @ CMU. SIGART Bulletin, n.d. Web. 25 Jan. 2017. <http://repository.cmu.edu/cgi/viewcontent.cgi?article=1346&context=compsci>.