How to Learn Picture Languages

How to Learn/What to Learn

Abst rac t : This paper discusses the kind of in fo rmat ion that must be present in a computer program that models the l i n g u i s t i c development of a c h i l d . A three stage model is presented that character izes the development of a na tu ra l l a n guage parser in a c h i l d of ages one, one and a h a l f , and two. Some data from ch i ld ren of these ages is presented. General prob...

Learning how to learn

In proportion to our body mass, our brain is three times as large as that of our nearest relatives. This huge organ is dangerous and painful to give birth to, expensive to build and, in a resting human, uses about 20 percent of the body's energy even though it is just 2 percent of the body's weight. There must be some reason for this evolutionary expense [1]. Recently, I lost one of my aunts. S...

How to learn multiple tasks

The paper examines the question of how learning multiple tasks interacts with neural architectures and the flow of information through those architectures. It approaches the question by using the idealization of an artificial neural network where it is possible to ask more precise questions about the effects of modular versus nonmodular architectures as well as the effects of sequential vs. sim...

On Drawn Symbolic Picture Languages

On Reversal-Bounded Picture Languages

Kim, C. and I.H. Sudborough, On reversal-bounded picture languages, Theoretical Computer Science 104 (1992) 185-206. For an integer k >O, a k-reversal-bounded picture language is a chain-code picture language which is described by a language L over the alphabet R= {u,d,r, I} such that, for every word x in L, the number of alternating occurrences of r’s and I’s in x is bounded by k. It is shown ...