A neural network model of learning mathematical equivalence

The typical structure of equations influences how we learn the meaning of the equal sign. Previous studies have shown that as students gain experience with addition problems, they actually perform worse on certain problems, before eventually improving. We seek to explain this trajectory with gradual implicit learning, without explicit representation of strategies or principles. Our parallel distributed processing model is nevertheless able to simulate several phenomena observed in how children learn mathematical equivalence: not only how successful performance develops, but also what strategies are used and how equations are encoded.

[1]  James L. McClelland.  Parallel Distributed Processing: Implications for Cognition and Development , 1988 .

[2]  James L. McClelland,et al.  Understanding normal and impaired word reading: computational principles in quasi-regular domains. , 1996, Psychological review.

[3]  Bethany Rittle-Johnson,et al.  Assessing Knowledge of Mathematical Equivalence: A Construct-Modeling Approach. , 2011 .

[4]  Marco Zorzi,et al.  Computational Modeling of Numerical Cognition , 2004 .

[5]  Martha W. Alibali,et al.  Middle-School Students' Understanding of the Equal Sign: The Books They Read Can't Help , 2006 .

[6]  J. Piaget,et al.  Child's Conception Of Geometry , 1960 .

[7]  Susan Goldin-Meadow,et al.  Transitional knowledge in the acquisition of concepts , 1988 .

[8]  Martha W. Alibali,et al.  You'll see what you mean: Students encode equations based on their knowledge of arithmetic , 2004, Cogn. Sci..

[9]  James L. McClelland,et al.  Sentence comprehension: A parallel distributed processing approach , 1989, Language and Cognitive Processes.

[10]  B. Rittle-Johnson,et al.  Conceptual and procedural knowledge of mathematics: Does one lead to the other? , 1999 .

[11]  Roberto Araya,et al.  A computational model of conscious and unconscious strategy discovery. , 2005, Advances in child development and behavior.

[12]  Emily R. Fyfe,et al.  Benefits of practicing 4 = 2 + 2: nontraditional problem formats facilitate children's understanding of mathematical equivalence. , 2011, Child development.

[13]  Robert M. Capraro,et al.  Changes in Equality Problem Types Across Four Decades in Four Second and Sixth Grade Textbook Series , 2012 .

[14]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[15]  Robert M. Capraro,et al.  Sources of Differences in Children's Understandings of Mathematical Equality: Comparative Analysis of Teacher Guides and Student Texts in China and the United States , 2008 .

[16]  James L. McClelland,et al.  U-Shaped Curves in Development: A PDP Approach , 2004, Journal of Cognition and Development.

[17]  James L. McClelland,et al.  On learning the past-tenses of English verbs: implicit rules or parallel distributed processing , 1986 .

[18]  Nicole M. McNeil.  U-shaped development in math: 7-year-olds outperform 9-year-olds on equivalence problems. , 2007, Developmental psychology.

[19]  Martha W. Alibali,et al.  Does Understanding the Equal Sign Matter? Evidence from Solving Equations , 2006 .

[20]  C. Lebiere,et al.  The Atomic Components of Thought , 1998 .

[21]  Michelle Perry,et al.  Learning and Transfer: Instructional Conditions and Conceptual Change , 1991 .

[22]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[23]  James L. McClelland,et al.  Structure and deterioration of semantic memory: a neuropsychological and computational investigation. , 2004, Psychological review.

[24]  P. Kellman,et al.  Perceptual Learning, Cognition, and Expertise , 2013 .

[25]  Sarah R Powell,et al.  Equations and the Equal Sign in Elementary Mathematics Textbooks , 2012, The Elementary School Journal.