Learning to search: From weak methods to domain-specific heuristics

Learning from experience involves three distinct components—generating behavior, assigning credit, and modifying behavior. We discuss these components in the context of learning search heuristics, along with the types of learning that can occur. We then focus on SAGE, a system that improves its search strategies with practice. The program is implemented as a production system, and learns by creating and strengthening rules for proposing moves. SAGE incorporates five different heuristics for assigning credit and blame, and employs a discrimination process to direct its search through the space of rules. The system has shown its generality by learning heuristics for directing search in six different task domains. In addition to improving its search behavior on practice problems, SAGE is able to transfer its expertise to scaled-up versions of a task, and in one case, transfers its acquired search strategy to problems with different initial and goal states.     

Planning and acting

A new theory of problem solving is presented, which embeds problem solving in the theory of action; in this theory, a problem is just a difficult action. Making this work requires a sophisticated language for-talking about plans and their execution. This language allows a broad range of types of action, and can also be used to express rules for choosing and scheduling plans. To ensure flexibility, the problem solver consists of an interpreter driven by a theorem prover which actually manipulates formulas of the language. Many examples of the use of the system six given. including an extended treatment of the world of blocks. Limitations and extensions of the system are discussed at length. It is concluded that a rule-based problem solver is necessary and feasible, but that much more work remains to be done on the underlying theory of planning and acting.     

An attempt to understand students' understanding of basic algebra

This paper reports the results obtained with a group of 24 14-year-old students when presented with a set of algebra tasks by the Leeds Modelling System, LMS. These same students were given a comparable paper-and-pencil test and detailed interviews some four months later. The latter studies uncovered several kinds of student misunderstandings that LMS had not detected. Some students had profound misunderstandings of algebraic notation: Others used strategies such as substituting numbers for variables until the equation balanced. Additionally, it appears that the student errors fall into several distinct classes: namely, manipulative, parsing, clerical, and “random.” LMS and its rule database have been enhanced as the result of this experiment, and LMS is now able to diagnose the majority of the errors encountered in this experiment. Finally, the paper gives a process-oriented explanation for student errors, and re-examines related work in cognitive modelling in the light of the types of student errors reported in this experiment. Misgeneralization is a mechanism suggested to explain some of the mal-rules noted in this study.     

Rules and topics in conversation

Rules of conversation are given that specify what can follow what. A system for deciding what makes a reasonable subject for a conversation is shown. Topics are discussed and rules for topic shift are presented.     

A learning algorithm for boltzmann machines

The computational power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections can allow a significant fraction of the knowledge of the system to be applied to an instance of a problem in a very short time. One kind of computation for which massively parallel networks appear to be well suited is large constraint satisfaction searches, but to use the connections efficiently two conditions must be met: First, a search technique that is suitable for parallel networks must be found. Second, there must be some way of choosing internal representations which allow the preexisting hardware connections to be used efficiently for encoding the constraints in the domain being searched. We describe a general parallel search method, based on statistical mechanics, and we show how it leads to a general learning rule for modifying the connection strengths so as to incorporate knowledge about a task domain in an efficient way. We describe some simple examples in which the learning algorithm creates internal representations that are demonstrably the most efficient way of using the preexisting connectivity structure.     

Hemispheric asymmetry in memory search for four-letter names and human faces

Two memory search experiments were conducted using vertically oriented four-letter names and human faces as stimuli. Subjects were required to indicate as quickly and as accurately as possible whether or not a single probe stimulus (presented for 150 msec to either the left or right visual field) was contained in a set of 2, 3, 4, or 5 items being held in short-term memory. The probe stimuli were presented alone (clear condition) or centrally embedded in a matrix of dots (degraded condition). In Experiment 1 (involving names), a right visual field/left hemisphere advantage was obtained and pinpointed at the encoding stage rather than at the memory comparison stage of the information-processing system. For Experiment 2 (involving human faces), no hemispheric advantage was readily observed. In each experiment, both the left hemisphere and the right hemisphere employed an abstract memory comparison operation from which the effects of probe degradation have been removed. These results are discussed in terms of their implications for various models of hemispheric asymmetry.     

On ego development and the structure of personality

present a theory of ego development as composed of several substructures related so that achievement of a given stage in one substructure is necessary but not sufficient for achieving the corresponding stage of another. The postulation of an exact relation belies what is known of the texture of human behavior and is premature in the absence of precise measurement of the several substructures and precise matching of stages. An alternative, the empirical method of simultaneously constructing a measure of ego development and portraits of the several stages, which Snarey et al. criticize for lack of strict logical coherence, is in the best tradition of contemporary science. The stage portraits are “prototypes” or “fuzzy sets.” Any mental structure can be divided into substructures, but the most general, superordinate structure is likely to prove most useful.