Grossberg, S. and Kuperstein, M. (1989) Neural Dynamics of Adaptive Sensory--Motor Control, Pergamon Press  Home/Search   Document Not in Database   Summary   Related Articles   Check

....connected. From engineering viewpoint, time varying behaviors are probably of greater importance among the nonlinear dynamic behaviors that recurrent neural networks manifest. Many authors have studied recurrent neural network models of various types of perceptual processes and applications [1] [2], 31, 41, 5] 61, 71. One of the dynamic behaviors concerned by many works [8] 9] 10] 11] 12] is that the existence and the location of equilibrium points, and with the qualitative properties of the equilibria. The stability analysis and applications of a class of single layered, ....

. Stephen Grossberg and Michael Kuperstein, Neural Dynamics of Adaptive Sensory-Motor Control: Ballistic Eye Movements, Elsevier / North Holland, Amsterdam, 1986.

....third approach entails the creation of a robot trajectory given only its initial and nal (target) positions. The robot receives sensory information from the workspace and autonomously constructs some kind of inverse mapping. Typical examples of this approach are the works of Grossberg Kuperstein [13], Kuperstein Rubinstein [14] Martinez et al. 15] and Ritter et al. 16] The three rst works describe a self organizing model for visuomotor coordination of a robot arm. This model learns to control a 5 degree of freedom (DOF) robot arm to reach cylindrical objects. The authors use a set of ....

S. Grossberg and M. Kuperstein. Neural dynamics of adaptive sensory-motor control. Elsevier, Amsterdam, 1986.

....the sensory cell and, hence, of the MP circuit. Figure 8(a) shows the output from the sensory cell. This circuit gives ARBIB the ability to ignore constant stimuli through habituation, and yet dishabituate to a change in stimulus strength. The P1 neurons form a simple position threshold slope map (Grossberg and Kuperstein 1986) that converts different input intensities to different positions of firing activity in an array of neurons. Here, with an array of just two P1 cells, ARBIB can differentiate between high and low firing rates of the sensory cell. There is a hierarchy of MP2 cells in which the P1 HIGH cell inhibits ....

Grossberg, S. and M. Kuperstein (1986). Neural Dynamics of Adaptive Sensory-Motor Control. Amsterdam: Elsevier (North-Holland).

....positions where inputs are expected, and its suggestions were always adopted by VISOR. of actions discovered by chance induces learning of intentional actions. This characteristic is a very powerful learning principle and has been incorporated in neural network modeling as well (see e.g. Grossberg and Kuperstein, 1989). It is also central in VISOR s learning of new schemas. When VISOR first encounters a new object, it focuses attention only at positions where there are inputs in the scene. After VISOR has formed a schema for the object, it will shift attention to places where the object parts are expected. In ....

Grossberg, S., and Kuperstein, M. (1989). Neural Dynamics of Adaptive Sensory-Motor Control. New York: Pergamon Press.

....input and output stimulus and response but it may also be the case that feedback from the environment can function as a form of supervision , albeit a noisy one. The idea of using vision to provide feedback has been studied in a variety of contexts, including control of eye movements [66], coordination of hand and eye movement [67, 68] and object recognition and manipulation [69] The precise form of the feedback and learning mechanisms vary, but 22 Image T u u u 1 y y World State T w 1 j j T v 1 System State Figure 12: Transformations in active vision. Changes ....

S. Grossberg and M. Kuperstein,Neural Dynamics of Adaptive Sensory-Motor Control, Oxford, Pergamon, 1989.

....This example illustrates an important characteristic of circular reaction: the repeated practice of actions discovered by chance induces learning of intentional actions. This characteristic is a very powerful learning principle and has been incorporated in neural network modeling as well (see e.g. Grossberg and Kuperstein, 1989). It is also central in VISOR s learning of new schemas. When VISOR first encounters a new object, it focuses attention only at positions where there are inputs in the scene. After VISOR has formed a schema for the object, it will shift attention to places where the object parts are expected. In ....

Grossberg, S., and Kuperstein, M. (1989). Neural Dynamics of Adaptive Sensory-Motor Control. New York: Pergamon Press.

....the same schema net remains most active and its weights are further modified to encode other parts of the object. After presentations of several different instances, the weights of the schema net will gradually 2 Multi modular learning schemes have also been proposed by Grossberg and Kuperstein [9], and Miikkulainen [15] converge to stable values that encode the essential structure of the object, and allow it to recognize further instances with minor variation. At the same time, the Response Module learns to associate the target response with the activation of this particular schema net. ....

Grossberg, S., and Kuperstein, M. (1989). Neural Dynamics of Adaptive Sensory-Motor Control. New York: Pergamon Press.

....An understanding of how these animals search for food and avoid danger by smell can be useful for industrial applications such as tracking the source of air pollution by a mobile robot. Over the years, research on sensory motor coordination has attracted an increasing amount of interests (e.g. [3, 5, 1, 8]) However, these works have been focused almost exclusively on visuomotor coordination. Studies of olfactory motor coordination, on the other hand, have been lacking. This paper describes the olfactory motor network of a simulated creature that can search for food and avoid danger by smell. We ....

S. Grossberg and M. Kuperstein. Neural Dynamics of Adaptive Sensory-Motor Control. Pergamon Press, New York, 1989.

....she likes. Circular reaction, therefore, is the idea that the repeated practice of actions discovered by chance induces learning of intentional actions. This is a very powerful learning principle and has been used, for example, to model the human visual saccade (Cohen et al. 1988; Grossberg 1978; Grossberg and Kuperstein 1989) and to build intelligent robots that learn 100 90 80 70 60 50 40 30 20 10 0 0.0 0.2 0.4 0.6 0.8 1.0 duck rabbit step activity Figure 18: Perceptual reversal mediated by top down input and neural satiation. A top down activation of 0.05 was fed into the rabbit schema s output unit. As a result, ....

Grossberg, S., and Kuperstein, M. (1989). Neural Dynamics of Adaptive Sensory-Motor Control.

....mapped onto one another through a learning process. Gain Learning and Map Learning There are at least two key types of saccadic learning: gain learning and map learning. Gain learning is proposed to take place in the cerebellum (Grossberg, 1969; Marr, 1969; Albus, 1971; Fujita, 1982; Ito, 1984; Grossberg Kuperstein, 1986; Dean, Mayhew, Langdon, 1994; Fiala, Grossberg, Bullock, 1996; Grossberg Merrill, 1996; Houk, Buckingham, Barto, 1996) where it uses visual error signals due to incorrect saccades to adaptively tune the total input amplitude that reaches the saccade generator in the reticular formation, ....

....coordinate system, to control saccadic movement parameters that are coded in a motor error coordinate system. Map learning can occur in several parts of the brain that are implicated in saccadic control, including the posterior parietal cortex, prefrontal cortex, and superior colliculus (Grossberg and Kuperstein, 1986; Zipser and Anderson, 1988; Grossberg, Roberts, Aguilar, and Bullock, 1996) Step Task A number of researchers have studied saccadic learning, and this work provides a powerful probe of the saccadic control circuits (Fitzgibbon, Goldberg, Segraves, 1986; Frens 2 van Opstal, 1994; Deubel, ....

[Article contains additional citation context not shown here]

Grossberg, S., & Kuperstein, M. (1986). Neural dynamics of adaptive sensory-motor control.

.... (Ito, 1984 and Figure 1) within the sensory motor system, support a view of the cerebellum as an adaptive controller capable of calibrating parallel feedforward motor commands that can substitute for slow feedback based commands and thereby enable high speed and accuracy without iterations (Grossberg and Kuperstein, 1986). Relatedly, the cerebellum has been viewed by some as an adaptive calibrator of internal forward models that allow computation of the expected effects of motor commands (Kawato and Gomi, 1991; Miall, Malkmus, and Robertson, 1996) This application of a cerebellar side loop would allow ....

....timing of these reflexes. These effects may be explained using modest extensions to the model proposed in Figure 2, through a more complete analysis of how NIP RN outputs to spinal cord affect the processing of sensory feedback during arm movement control. Comparison with other cerebellar models Grossberg and Kuperstein (1986) developed a model of error based opponent learning of adaptive gain control by the cerebellum. This work built on Grossberg s (1969) cerebellar model, which suggested that both LTD and LTP occurred at the parallel fiberPurkinje cell synapse to learn to control linearly ordered motor components. ....

[Article contains additional citation context not shown here]

Grossberg, S., and Kuperstein, M. (1986). Neural dynamics of adaptive sensorymotor control. Elmsford, N.Y. Pergamon Press.

.... 1992, 1994; Cohen and Grossberg, 1986, 1987; Grossberg, 1978; Grossberg and Stone, 1986a) Interactions between such a working memory and its list categories have been used to explain data from experiments about the sequential performance of stored motor commands (Boardman and Bullock, 1991; Grossberg and Kuperstein, 1989), about errors in serial item and order recall due to rapid visual attention shifts (Grossberg and Stone, 1986a) about errors and reaction times during lexical priming and episodic memory experiments (Grossberg and Stone, 1986b) and about data concerning word superiority, phonemic restoration, ....

Grossberg, S. and Kuperstein, M. (1989). Neural dynamics of adaptive sensory-motor control: Expanded edition. Elmsford, NY: Pergamon Press.

.... 1988; Optican and Robinson, 1980; Thompson, 1988; Thompson et al. 1984, 1987) Models of cerebellar learning have been developed over the years to help explain these motor conditioning data (Albus, 1971; Bullock, Fiala, and Grossberg, 1994; Fujita, 1982a, 1982b; Grossberg, 1969b, 1972b; Grossberg and Kuperstein, 1986; Ito, 1984; Lisberger, 1988; Marr, 1969) A third line of research on learning and memory concerns cognitive emotional interactions, including how a conditioned stimulus (CS) such as a tone or light, when paired with an unconditioned stimulus (US) such as a shock, can learn to generate ....

....egorized by another ART network, whose active nodes are said to code list categories. This list categorization process has been proved to retain its stability even as new information continues to be stored in the working memory through time (Bradski, Carpenter, and Grossberg, 1992, 1994; Cohen and Grossberg, 1986, 1987; Grossberg, 1978; Grossberg and Stone, 1986a) Interactions between such a working memory and its list categories have been used to explain data from experiments about the sequential performance of stored motor commands (Boardman and Bullock, 1991; Grossberg and Kuperstein, 1989) about ....

[Article contains additional citation context not shown here]

Grossberg, S. and Kuperstein, M. (1986). Neural dynamics of adaptive sensory-motor control: Ballistic eye movements. Amsterdam: Elsevier/North-Holland.

No context found.

Grossberg, S. and Kuperstein, M. (1989) Neural Dynamics of Adaptive Sensory--Motor Control, Pergamon Press

No context found.

S. Grossberg and M. Kuperstein. Neural Dynamics of adaptive sensory-motor control: Ballistic eye movements. Amsterdam: Elsevier, 1986. 23

No context found.

Grossberg, S. & Kuperstein, M. (1986) Neural Dynamics of Adaptive Sensory-Motor Control: Ballistic Eye Movements. Amsterdam: Elsevier.

No context found.

S. Grossberg and M. Kuperstein, Neural dynamics of adaptive sensorymotor control. Pergamon Press, New York, second edition, 1989.

No context found.

Grossberg, S. and Kuperstein, M. Neural dynamics of adaptive sensory-motor control, Advances in Psychology, Vol.30, Elsevier Science Publishers, 1986

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC