Cüneyt GÜZELİŞ, Büyükaksoy Gülay KAPLAN, Neslihan S. ŞENGÖR

Prefrontal korteks işlevlerinin yapay sinir ağları ile modellenmesi

Bu çalışmada, değerlendirme testleri ile ölçülmeye çalışılan prefrontal korteks işlevlerini modellemek amacıyla işlemsel modeller önerilmiştir. Modelleme aracı olarak, yapay sinir ağları kullanılmıştır. Literatürde prefrontal korteksin amaca yönelik davranış geliştirmek için gerekli olan yüksek seviyeli bilişsel işlevlerden sorumlu olduğu önerilmektedir. Bu çalışmada esneklik, soyut düşünme ve amaca yönelik davranış geliştirme işlevlerini ölçmekte sıklıkla kullanılan Wisconsin Kart Eşleştirme Testi ve Stroop testi ele alınmıştır. Her iki test için önerilen modellerin sağlam ve prefrontal hasarlı deneklerin performanslarını üretebilme yetenekleri benzetimler ile sınanmıştır. Benzetim sonuçları modellerin klinik verilere uygun sonuçlar ürettiğini göstermektedir.

Modeling prefrontal cortex functions using artificial neural networks

In this work, computational models for prefrontal cortex functions during the evaluation tests are proposed. Artificial neural networks are used as modeling tools. In the literature the prefrontal cortex is suggested to be responsible for high order cognitive abilities needed for goal-directed behavior. Wisconsin Card Sorting Test and Stroop test which are the representative ones for measuring mental flexibility, abstract thinking and goal directed behavior are considered in this work. The first step of modeling approach taken in this work is to propose the hypothetical tasks/subtasks which are supposed to be performed by the subject to complete considered tests successfully. At the same time these tasks must be defined in terms of the processes which are executed by the prefrontal circuits. After the test material and application of the test are simulated in a software environment which is developed using MATLAB®, the tests are applied to the model and the results are scored following the test evaluation rules like a real subject. The most important point of the modeling is to simulate the behavior of the PFC.

PDF

___

Amos, A., (2000). A computational model of information processing in the frontal cortex and basal ganglia, Journal of Cognitive NeuroScience 12, 505-519.
Bose, N. ve Liang, P., (1996). Neural network fundamentals with graphs, algorithms and applications, Mc Graw-Hill, NY.
Brown, L., Schneider, J. ve Lidsky, T., (1997). Sensory and cognitive functions of the basal ganglia, Current Opinion in Neurobiology, 7, 157-163.
Dehaene, S., Changeux, J.P., (1991). The Wisconsin card sorting test: theoretical analysis and modeling in a neuronal network, Cerebral Cortex, 1, 62-79.
Fuster, J.M. (1997). The prefrontal cortex, Lippincott- Raven, Philadelphia.
Heaton, R.K., Chelune, G.S., Talley, J.L., Kay, G.G. Curtis, C., (1993). Wisconsin card sorting test. Psychological Assessment Resources.
Hopfield, J., (1982). Neural networks and physical systems with emergent collective computational abilities, PNAS, 79, 2554-2558.
Kaplan, G.B., Genç, İ. Güzeliş, C., (2001). A simple neural network system for Wisconsin Card Sorting Test, Proc. EMBC 2001.
Leven, S., Levine, D., (1987). Effects of reinforcement on knowledge retrieval and evaluation,IEEE First ICNN, 2, 269-279.
Lezak, M. (1985). Neuropsychological Assessment, 2nd Eddition, Oxford University Press.
MacLeod, C., (1991). Half a century of research on Stroop effect: An integrative review, Psychological Bulletin, 109, 163-203.
Mehrotra, K., Mohan, K. ve Ranka, S., (1997). Elements of Artificial Neural Networks, The MIT Press, Massachusetts.
Monchi, O., Taylor, J.G., Dagher, A., (2000). A neural model of working memory processes in normal subjects, Parkinson's disease and schizophrenia for fMRI design and predictions, Neural Networks, 3, 953-973.
Weintraub, S. (2000). Neuropsychological assessment of mental state, in Mesulam ed, Principles of Behavioural and Cognitive Neurology, 121-173, Oxford University Press, Oxford.
Zurada, J., (1992). Introduction to artificial neural systems, West Publishing Company, St. Paul.