A framework for ICAI systems based on inductive inference and logic programming

Kawai, Kazuhisa; Mizoguchi, Riichiro; Kakusho, Osamu; Toyoda, J.

doi:10.1007/bf03037461

Cited by 7 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First Run. Running algorithmic debugging on the expert program and the learner's solution concludes the dialogue (now omitted) with the disagreement add_ten_to_minuend ( 3,4,14) and the cause "missing". The code perturbation algorithm makes use of Delete-CallToClause/2 to delete the subgoal add ten to minuend/3 from the first program clause of process column/3; the single occurrence of its output variable M10 is replaced by its input variable M in the subsequent calls to take difference/4 and append/3.…”

Section: Complex Error Of Omission and Commissionmentioning

confidence: 99%

See 1 more Smart Citation

Program Analysis and Manipulation to Reproduce Learners’ Erroneous Reasoning

Zinn

2013

Logic-Based Program Synthesis and Transformation

View full text Add to dashboard Cite

Pedagogical research shows that learner errors are seldom random but systematic. Good teachers are capable of inferring from learners' input the erroneous procedure they are following, and use the result of such deep cognitive diagnoses to repair its incorrect parts. We report a method for the automatic reconstruction of such erroneous procedures based on learner input and the analysis and manipulation of logic programs. The method relies on an iterative application of two algorithms: an innovative use of algorithmic debugging to identify learner errors by the analysis of (initially) correct (sic) Prolog-based procedures, and a subsequent program manipulation phase where errors are introduced into (initially) correct procedures. The iteration terminates with the derivation of an erroneous procedure that was followed by the learner. The procedure, and its step-wise reconstruction, can then be used to inform remedial feedback.

show abstract

Section: Complex Error Of Omission and Commissionmentioning

confidence: 99%

“…Sums are encoded as Prolog lists of columns, where a column is represented as 3-element term (M, S, R) representing minuend, subtrahend, and result cell. 3 The program code implements the decomposition method.…”

Section: Introductionmentioning

confidence: 99%

Program Analysis and Manipulation to Reproduce Learners’ Erroneous Reasoning

Zinn

2013

Logic-Based Program Synthesis and Transformation

View full text Add to dashboard Cite

show abstract

“…They found that this technical improvement converted a CBI system in an effective and interesting tool for providing training. In the year 1987, Kazuhisa Kawai et al [26] proposed a new ICAI (Intelligent Computer-Assisted Instruction) system. This system had two main modules expertise and the student module.…”

Section: Different Expert Systems For Assisting and Improving Teachinmentioning

confidence: 99%

Survey of Expert Systems and the Cognitive Approaches towards an Effective Tutoring System

Chaturvedi¹,

Prajapati²

2015

IJCA

View full text Add to dashboard Cite

This paper presents a survey of Expert Tutoring System (ETS), designed for the improvement of teaching pedagogy. It talks about the flaws and designing issues that may occur in designing the expert tutoring system, and also suggests the cognitive approach for building a robust tutoring system. It describes the ill defined domains, case based reasoning, and the system approach for the designing of a cognitive tutoring system.

show abstract

“…In [3], Kawai et al also represent expert knowledge as a set of Prolog clauses; Shapiro's Model Inference System (MIS) [6], following an inductive logic programming approach, is used to synthesize learners' (potentially erroneous) procedure from expert knowledge and student answers. Once the procedure to fully capture learner behaviour is constructed, Shapiro's Program Diagnosis System, based upon standard algorithmic debugging, is used to identify students' misconceptions, i.e., the bugs in the MIS-constructed program.…”

Section: Related Workmentioning

confidence: 99%

Algorithmic Debugging for Intelligent Tutoring: How to Use Multiple Models and Improve Diagnosis

Zinn

2013

KI 2013: Advances in Artificial Intelligence

View full text Add to dashboard Cite

Intelligent tutoring systems (ITSs) are capable to intelligently diagnose learners' problem solving behaviour only in limited and well-defined contexts. Learners are expected to solve problems by closely following a single prescribed problem solving strategy, usually in a fixedorder, step by step manner. Learners failing to match expectations are often met with incorrect diagnoses even when human teachers would judge their actions admissible. To address the issue, we extend our previous work on cognitive diagnosis, which is based on logic programming and meta-level techniques. Our novel use of Shapiro's algorithmic debugging now analyses learner input independently against multiple models. Learners can now follow one of many possible algorithms to solve a given problem, and they can expect the tutoring system to respond with improved diagnostic quality, at negligible computational costs.

show abstract

A framework for ICAI systems based on inductive inference and logic programming

Cited by 7 publications

References 3 publications

Program Analysis and Manipulation to Reproduce Learners’ Erroneous Reasoning

Program Analysis and Manipulation to Reproduce Learners’ Erroneous Reasoning

Survey of Expert Systems and the Cognitive Approaches towards an Effective Tutoring System

Algorithmic Debugging for Intelligent Tutoring: How to Use Multiple Models and Improve Diagnosis

Contact Info

Product

Resources

About