Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories

Gaudiano, Paolo; Grossberg, Stephen

doi:10.1016/0893-6080(91)90002-m

Cited by 138 publications

(92 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To meet these requirements, the current model was formulated as an adaptive neural network whose speech January3J, 1995 production properties were verified through computer simulation. This model brings together contributions from many researchers, including the use of an action-perception or babbling cycle to tune model parameters (Bullock eta!., 1993;Gaudiano and Grossberg, 1991), the use of coordinative stmctures (Easton, 1972;Fowler, 1980;Saltzman and Munhall, 1989), the use of orosensory information for target specification (Lindblom et a!., 1979;Perkell, 1980), the incorporation of constriction locations and degrees in this target specification (Saltzman and Munhall, 1989), the use of target ranges rather than positions (Keating, 1990;Manuel, 1987Manuel, , 1990, the use of a continuum from hyperarticulation to hypoarticulation (Lindblom, 1990), the use of a look-ahead process for anticipatory coarticulation (Henke, 1966;Kozhevnikov and Chistovich, 1965), the incorporation of a multiplicative gating signal for volitional speed conU'ol (Bullock and Grossberg, 1988), and the use of a direction-to-velocity mapping to gain motor equivalence capabilities (Bullock et al, 1993;Guenther, 1992).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Speech sound acquisition, coarticulation, and rate effects in a neural network model of speech production.

Guenther

1995

Psychological Review

379

351

View full text Add to dashboard Cite

This article describes a neural network model of speech motor skill acquisition and speech production that explains a wide range of data on variability, motor equivalence, coarticulation, and rate effects. Model parameters are learned during a babbling phase. To explain how infants learn language-specific variability limits, speech sound targets take the form of convex regions, rather than points, in orosensory coordinates. Reducing target size for better accuracy during slower speech leads to differential effects for vowels and consonants, as seen in experiments previously used as evidence for separate control processes for the 2 sound types. Anticipatory coarticulation arises when targets are reduced in size on the basis of context; this generalizes the well-known look-ahead model of coarticulation. Computer simulations verify the model's properties.The primary goal of the modeling work described in this article is to provide a coherent theoretical framework that provides explanations for a wide range of data concerning the articulator movements used by humans to produce speech sounds. This is carried out by formulating a model that transforms strings of phonemes into continuous articulator movements for producing these phonemes. This study of speech production is largely motivated by the following question of speech acquisition: How does an infant acquire the motor skills needed to produce the speech sounds of his or her native language? Speech production involves complex interactions among several different reference frames. A phonetic frame describes the sounds a speaker wishes to produce, and the signals that convey these sound units to a listener exist within an acoustic frame. Tactile and proprioceptive signals form an orosensory frame (e.g., Perkell, 1980) that describes the shape of the vocal tract, and the muscles controlling the positions of individual articulators make up an articulatory frame. The parameters governing the interactions among these frames cannot be fixed at birth. One reason for this is the language specificity of these interactions. For example, English listeners distinguish between the sounds /r/ and /!/, but Japanese listeners do not. Corresponding differences are seen in the articulator movements of the two groups (Miyawaki et al., 1975). Thus, despite some obvious commonalities between the phonetics of different languages (e.g., widespread use of consonants like /d/, /n/, and /s/ across the world's languages), the precise nature of mappings between acoustic goals and articulator movements depends on the lanThis research was supported in part by Air Force Office of Scientific Research F49620-92-J-0499. I would like to thank Dan Bullock and Elliot Saltzman for their insightful suggestions on an earlier

show abstract

Section: Discussionmentioning

confidence: 99%

“…The neural mechanism used to learn the convex region targets in DIVA is related to the Vector Associative Map detailed in Gaudiano and Grossberg (1991). The learning laws governing modification of the synaptic weights are:…”

Section: Learning Sound Targets: the Phonetic-to-orosensory Mappingmentioning

confidence: 99%

Speech sound acquisition, coarticulation, and rate effects in a neural network model of speech production.

Guenther

1995

Psychological Review

379

351

View full text Add to dashboard Cite

show abstract

“…W e h a v e shown, in a series of articles, how head-centered and body-centered representations of an object's spatial location and orientation may be learned and used to control reaches of the hand-arm system that can continuously adapt themselves to changes in the sensory and motor apparatus that is used to plan and execute reaching behaviors Carpenter, Grossberg, and Lesher, 1998;Gaudiano and Grossberg, 1991;Grossberg, Guenther, Bullock, and Greve, 1993;Guenther, Bullock, Greve, and Grossberg, 1994). None of these model circuits has resonant loops; hence, they do not support consciousness.…”

Section: Corticohippocampal Interactions and Medial Temporal Amnesiamentioning

confidence: 99%

“…Models such a s A R T quantify how excitatory matching is accomplished. A di erent t ype of model, called a Vector Associative Map, or VAM, model, suggests how inhibitory matching is accomplished (Gaudiano and Grossberg, 1991;Grossberg, Guenther, Bullock, and Greve, 1993;Guenther, Bullock, Greve, and Grossberg, 1994).…”

Section: Corticohippocampal Interactions and Medial Temporal Amnesiamentioning

confidence: 99%

The Link Between Brain Learning, Attention, and Consciousness

Grossberg

2009

Causality, Meaningful Complexity and Embodied Cognition

Self Cite

View full text Add to dashboard Cite

“…(Motor babbling can be observed in babies, where a repetitive actionperception cycle generates associative information between the various representations.) Action is generated through the Endogenous Random Generator (ERG) [2], which sends random motor commands, and the results of these actions Alexandros Bouganis and Murray Shanahan are with the Department of Computing, Imperial College London, UK (email: {alexandros.bouganis, m.shanahan}@imperial.ac.uk). in the spatial domain are perceived and associated.…”

mentioning

confidence: 99%

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Bouganis

Shanahan

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-In this paper, we present a spiking neural network architecture that autonomously learns to control a 4 degree-offreedom robotic arm after an initial period of motor babbling. Its aim is to provide the joint commands that will move the end-effector in a desired spatial direction, given the joint configuration of the arm. The spiking neurons have been simulated according to Izhikevich's model, which exhibits biologically realistic behaviour and yet is computationally efficient. The architecture is a feed-forward network where the input layers encode the intended movement direction of the end-effector in spatial coordinates, as well as the information that is given by proprioception about the current joint angles of the arm. The motor commands are determined by decoding the firing patterns in the output layers. Both excitatory and inhibitory synapses connect the input and output layers, and their initial weights are set to random values. The network learns to map input stimuli to motor commands during a phase of repetitive action-perception cycles, in which Spike Timing-Dependent Plasticity (STDP) strengthens synapses between neurons that are correlated and weakens synapses between uncorrelated ones. The trained spiking neural network has been successfully tested on a kinematic model of the arm of an iCub humanoid robot.

show abstract

Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories

Cited by 138 publications

References 46 publications

Speech sound acquisition, coarticulation, and rate effects in a neural network model of speech production.

Speech sound acquisition, coarticulation, and rate effects in a neural network model of speech production.

The Link Between Brain Learning, Attention, and Consciousness

Training a spiking neural network to control a 4-DoF robotic arm based on Spike Timing-Dependent Plasticity

Contact Info

Product

Resources

About