This paper considers steady-state and timedependent characteristics of the response of the hidden-layer neurons in a dynamic model for the neural network trained through supervised learning to perform transformation of input signals into output signals. This transformation is set up so as to correspond to variation in the directions of two-dimensional vectors and is treated as creation by the network of a “movement” direction in response to a “stimulus” direction. The input vector is encoded in the state of the input layer at the initial instant of time, and the output vector in the state of the output layer at great values of time. After the network has been trained on examples of the input-output relation, the hidden neurons turn out to be broadly tuned to direction. The corresponding dependence for their activity is approximated with a smooth function, whose maximum allows some preferred direction to be attributed to each neuron. If each hidden neuron is assigned a vector pointing in its preferred direction, then any arbitrarily chosen direction can be characterized by an imaginary neuronal population vector (Georgopoulos et al. 1986) defined as the sum of the vectors of preferred direction for the neurons, with the weights equal to their activities for the chosen direction. It is demonstrated that, although hidden neurons are broadly tuned to direction, the population vector points in a direction congruent with that of the input vector at the initial moment of time and accurately predicts the direction of the output vector at great values of time. In between, the population vector turns continuously from the one direction towards the other. The dynamic and stationary properties of the population vector of the hidden-layer neurons, as obtained within the framework of the model in question, show a close similarity to the experimentally observed (Georgopoulos et al. 1986; Georgopoulos et al. 1989) behaviour of the population vector constructed in the same manner on the ensemble of motor cortex neurons sensitive to a certain type of movement.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Anshelevich VV, Amirikian BR, Lukashin AV, Frank-Kamenetskii MD (1989) On the ability of neural network to perform generalization by induction. Biol Cybern 61:125–128
Carnevali P, Patarnello S (1987) Exhaustive thermodynamical analysis of Boolean learning networks. Europhys Lett 4:1199–1204
Churchland PS, Sejnowski TJ (1989) Perspectives on cognitive neuroscience. Science 242:741–745
Dehaene S, Changeux JP, Nadel JP (1987) Neural networks that learn temporal sequences by selection. Proc Natl Acad Sci USA 84:2727–2731
Del Giudice P, Franz S, Virasoro MA (1989) Perceptron beyond the limit of capacity. J Phys France 50:121–124
Georgopoulos AP, Schwartz AB, Kettner RE (1986) Neuronal population coding of movement direction. Science 233:1416–1419
Georgopoulos AP, Lurito JT, Petrides M, Schwartz AB, Massey JT (1989) Mental rotation of the neuronal population vector. Science 243:234–236
Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088–3092
Hopfield JJ, Tank DW (1986) Computing with neural circuits: a model. Science 233:625–633
Josin G (1988) Neural-space generalization of a topological transformation. Biol Cybern 59:283–290
Kirkpatrick S, Gelatt CD, Vecchi MP (1983) Optimization by simulated annealing. Science 220:671–680
Kuperstein M (1988) Neural model of adaptive hand-eye coordination for single postures. Science 239:1308–1311
Lehky SR, Sejnowski TJ (1988) Network model of shape-from-shading: neural function arises from both receptive projective fields. Nature 333:452–454
Lemon RN (1984) Methods for neuronal recording in conscious animals. Wiley, Chisester
Lisberger SG (1989) The neural basis for learning of simple motor skills. Science 242:728–735
Lockery SR, Wittenberg G, Kristan WB, Cottrell GW (1989) Function of identified interneurons in the leech elucidated using neural networks trained by back-propogation. Nature 340:468–471
Massone L, Bizzi E (1989) A neural network model for limb trajectory formation. Biol Cybern 61:417–425
Ritter HJ, Martinetz TM, Schulten KJ (1989) Topology-conserving maps for learning visuo-motor-coordination. Neural Networks 2:159–168
Rumelhart DE, McClelland JL (1986) Parallel distributed processing: Explorations in the microstructure of cognition, vols 1,2. MIT Press, Cambridge
Schöner G, Kelso JAS (1988) Dinamic pattern generation in behavioral and neural systems. Science 239:1513–1520
Wise SP, Desimone R (1989) Behavioral neurophysiology: Insights into seeing and grasping. Science 242:736–741
Zipser D, Anderson RA (1988) A back-propogation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature 331:679–684
About this article
Cite this article
Lukashin, A.V. A learned neural network that simulates properties of the neuronal population vector. Biol. Cybern. 63, 377–382 (1990). https://doi.org/10.1007/BF00202754
- Neural Network
- Motor Cortex
- Output Layer
- Input Vector
- Input Layer