Learning problem

Albert Pilot studied Chemistry at Utrecht Urriversity in The Netherlands, with a major in analytical chemistry and a minor in educational research. His PhD was in 1980 on learning problem solving in science at the University of Twente. In 1996 he was appointed as full professor of curriculirm development in IVLOS Institute of Education at Utrecht University and in 1998 also as professor of Chemistry Education in the Department of Chemistry of that university. His research in Chemistry Education is concentrated in the field of curricitlirm development, context-based education and professiorral development of teachers. 

Independently of the amount of data and the way they are acquired, the definition of the learning problem simulates a continuous data flow. Such... 

We are now ready to propose the basic algorithm for the solution of the learning problem. 

The solution to the learning problem should provide the flexibility to search for the model in increasingly larger spaces, as the inadequacy of the smaller spaces to approximate well the given data are proved. This immediately calls for a hierarchy in the space of functions. Vapnik (1982) has introduced the notion of structure as an infinite ladder of finitedimensional nested subspaces ... 

The space-frequency localization of wavelets has lead other researchers as well (Pati, 1992 Zhang and Benveniste, 1992) in considering their use in a NN scheme. In their schemes, however, the determination of the network involves the solution of complicated optimization problem where not only the coefficients but also the wavelet scales and positions in the input space are unknown. Such an approach evidently defies the on-line character of the learning problem and renders any structural adaptation procedure impractical. In that case, those networks suffer from all the deficiencies of NNs for which the network structure is a static decision. 

Finally, having set up the learning problem, we need to employ a learning method that will guarantee preservation of the correctness of the branch-and-bound algorithm and make useful additions to the control information we have about the problem (Section V). 

Conners Parent Questionnaire. Conners Parent Questionnaire (PQ) is a 94-item checklist of symptoms that evaluates common behavior disorders using a four-point scale in children up to 15 years of age and takes 15 to 20 minutes to complete. It is used once pretreatment and may be repeated but is often replaced after the first use by the 11-item Conners Parent-Teacher Questionnaire (PTQ). There are eight subscales conduct problem, anxiety, impulsive-hyperactive, learning problem, psychosomatic, perfectionism, antisocial, and muscular tension. 

It is indicated in mental retardation and learning problems in children, confusional state in old age, cerebrovascular accidents. 

More than 60,000 infants suffer from fetal alcohol syndrome (FAS), a condition that is largely irreversible and whose effects include serious developmental and learning problems. 

The error between the actual mismatch (obtained from the simulation results) and that predicted by the network is used as the error signal to train the network (see Figure 12.3). This is a classical supervised learning problem, where the system provides target values directly to the output co-ordinate system of the learning network. 

Dr. K does a physical examination of Michael but, more important, carefully listens to Mrs. S s concerns. He gives her a form for the teacher to complete. Dr. K asks Mrs. S to talk to the psychologist who works in his office. Although Mrs. S does not believe that Michael has any emotional or learning problems that warrant a meeting with a psychologist, she trusts Dr. K and so she agrees. 

Dessens AB, Cohen-Kettenis PT, Mellenbergh GJ, Koppe JG, van De Poll NE, Boer K. Association of prenatal phenobarbital and phenytoin exposure with small head size at birth and with learning problems. Acta Paediatr 2000 89(5) 533-41. 

---