scispace - formally typeset
Search or ask a question

Showing papers by "Michael I. Jordan published in 1997"


Book ChapterDOI
TL;DR: A theory of learned sequential behavior is presented, with a focus on coarticulatory phenomena in speech, implemented as a recurrent parallel distributed processing network that is trained via a generalized error-correcting algorithm.
Abstract: A theory of learned sequential behavior is presented, with a focus on coarticulatory phenomena in speech. The theory is implemented as a recurrent parallel distributed processing network that is trained via a generalized error-correcting algorithm. The basic idea underlying the theory is that both serial order and coarticulatory overlap can be represented in terms of relative levels of activation in a network if a clear distinction is made between the state of the network and the output of the network.

1,178 citations


Journal ArticleDOI
TL;DR: It is shown that the well-known forward-backward and Viterbi algorithms for HMMs are special cases of more general inference algorithms for arbitrary PINs and the existence of inference and estimation algorithms for more general graphical models provides a set of analysis tools for HMM practitioners who wish to explore a richer class of HMM structures.
Abstract: Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image processing, and genetics.Formalisms for manipulating these models have been developedrelatively independently in these research communities. In this paper weexplore hidden Markov models (HMMs) and related structures within the general framework of probabilistic independencenetworks (PINs). The paper contains a self-contained review of the basic principles of PINs.It is shown that the well-known forward-backward (F-B) and Viterbialgorithms for HMMs are special cases of more general inference algorithms forarbitrary PINs. Furthermore, the existence of inference and estimationalgorithms for more general graphical models provides a set of analysistools for HMM practitioners who wish to explore a richer class of HMMstructures.Examples of relatively complex models to handle sensorfusion and coarticulationin speech recognitionare introduced and treated within the graphical model framework toillustrate the advantages of the general approach.

293 citations


Journal ArticleDOI
TL;DR: The data support the hypothesis that unconstrained motions are, unlike compliant motions, not programmed to follow a straight-line path in the task space, and suggest that compliant and unconStrained movements involve different control strategies.
Abstract: Desmurget, Michel, Michael Jordan, Claude Prablanc, and Marc Jeannerod. Constrained and unconstrained movements involve different control strategies. J. Neurophysiol. 77: 1644–1650, 1997. This expe...

189 citations


Book ChapterDOI
TL;DR: A computational framework capturing this notion of an observer attempting to estimate its own state and the state of the environment by integrating multiple sources of information is described, suggesting that spatial information from visual and auditory systems is integrated so as to reduce the variance in localization.
Abstract: The sensorimotor integration system can be viewed as an observer attempting to estimate its own state and the state of the environment by integrating multiple sources of information. We describe a computational framework capturing this notion, and some specific models of integration and adaptation that result from it. Psychophysical results from two sensorimotor systems. subserving the integration and adaptation of visuo-auditory maps, and estimation of the state of the hand during arm movements. are presented and analyzed within this framework. These results suggest that: (1) Spatial information from visual and auditory systems is integrated so as to reduce the variance in localization. (2) The effects of a remapping in the relation between visual and auditory space can be predicted from a simple learning rule. (3) The temporal propagation of errors in estimating the hand's state is captured by a linear dynamic observer, providing evidence for the existence of an internal model which simulates the dynamic behavior of the arm.

160 citations


Journal ArticleDOI
TL;DR: This work explored whether the CNS plans arm movements based entirely on the visual space kinematics of the movements, or whether the planning process incorporates specific details of the biomechanical plant to optimize the trajectory plan.
Abstract: A novel obstacle avoidance paradigm was used to investigate the planning of human reaching movements. We explored whether the CNS plans arm movements based entirely on the visual space kinematics of the movements, or whether the planning process incorporates specific details of the biomechanical plant to optimize the trajectory plan. Participants reached around an obstacle, the tip of which remained fixed in space throughout the experiment. When the obstacle and the start and target locations were rotated about the tip of the obstacle, the visually specified task constraints retained a rotational symmetry. If movements are planned in visual space, as indicated from a variety of studies on planar point-to-point movements, the resulting trajectories should also be rotationally symmetric across trials. However, systematic variations in movement path were observed as the orientation of the obstacle was changed. These path asymmetries can be accounted for by a class of models in which the planner reduces the likelihood of collision with the obstacle by taking into account the anisotropic sensitivity of the arm to external perturbations or uncertainty in joint level control or proprioception. The model that best matches the experimental results uses planning criteria based on the inertial properties of the arm.

132 citations


Dissertation
01 Jan 1997
TL;DR: This thesis proposes a principled framework for approximating graphical models based on variational methods and develops variational techniques from the perspective that unifies and expands their applicability to graphical models.
Abstract: Graphical models enhance the representational power of probability models through qualitative characterization of their properties. This also leads to greater efficiency in terms of the computational algorithms that empower such representations. The increasing complexity of these models, however, quickly renders exact probabilistic calculations infeasible. We propose a principled framework for approximating graphical models based on variational methods. We develop variational techniques from the perspective that unifies and expands their applicability to graphical models. These methods allow the (recursive) computation of upper and lower bounds on the quantities of interest. Such bounds yield considerably more information than mere approximations and provide an inherent error metric for tailoring the approximations individually to the cases considered. These desirable properties, concomitant to the variational methods, are unlikely to arise as a result of other deterministic or stochastic approximations. The thesis consists of the development of this variational methodology for probabilistic inference, Bayesian estimation, and towards efficient diagnostic reasoning in the domain of internal medicine. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)

111 citations


Journal ArticleDOI
TL;DR: The results of this experiment showed that both the systematic and the variable errors were significantly lower in the SCL than in the FOL condition, which suggests that the effect of viewing the static hand prior to motion does not only depend on the simultaneous vision of the goal and the effector during movement planning.
Abstract: It is now well established that the accuracy of pointing movements to visual targets is worse in the full open loop condition (FOL; the hand is never visible) than in the static closed loop condition (SCL; the hand is only visible in static position prior to movement onset). In order to account for this result, it is generally admitted that viewing the hand in static position (SCL) improves the movement planning process by allowing a better encoding of the initial state of the motor apparatus. Interestingly, this wide-spread interpretation has recently been challenged by several studies suggesting that the effect of viewing the upper limb at rest might be explained in terms of the simultaneous vision of the hand and target. This result is supported by recent studies showing that goal-directed movements involve different types of planning (egocentric versus allocentric) depending on whether the hand and target are seen simultaneously or not before movement onset. The main aim of the present study was to test whether or not the accuracy improvement observed when the hand is visible before movement onset is related, at least partially, to a better encoding of the initial state of the upper limb. To address this question, we studied experimental conditions in which subjects were instructed to point with their right index finger toward their unseen left index finger. In that situation (proprioceptive pointing), the hand and target are never visible simultaneously and an improvement of movement accuracy in SCL, with respect to FOL, may only be explained by a better encoding of the initial state of the moving limb when vision is present. The results of this experiment showed that both the systematic and the variable errors were significantly lower in the SCL than in the FOL condition. This suggests: (1) that the effect of viewing the static hand prior to motion does not only depend on the simultaneous vision of the goal and the effector during movement planning; (2) that knowledge of the initial upper limb configuration or position is necessary to accurately plan goal-directed movements; (3) that static proprioceptive receptors are partially ineffective in providing an accurate estimate of the limb posture, and/or hand location relative to the body; and (4) that static visual information significantly improves the representation provided by the static proprioceptive channel.

109 citations


Proceedings Article
01 Dec 1997
TL;DR: This paper derives an efficient algorithm for updating the mixture parameters and applies it to the problem of learning in sigmoid belief networks and demonstrates a systematic improvement over simple mean field theory as the number of mixture components is increased.
Abstract: Exact inference in densely connected Bayesian networks is computationally intractable, and so there is considerable interest in developing effective approximation schemes. One approach which has been adopted is to bound the log likelihood using a mean-field approximating distribution. While this leads to a tractable algorithm, the mean field distribution is assumed to be factorial and hence unimodal. In this paper we demonstrate the feasibility of using a richer class of approximating distributions based on mixtures of mean field distributions. We derive an efficient algorithm for updating the mixture parameters and apply it to the problem of learning in sigmoid belief networks. Our results demonstrate a systematic improvement over simple mean field theory as the number of mixture components is increased.

87 citations


Proceedings Article
01 Jun 1997
TL;DR: A family of efficient algorithms that use EM and the Minimum Spanning Tree algorithm to find the ML and MAP mixture of trees for a variety of priors, including the Dirichlet and the MDL priors are presented.
Abstract: This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EM and the Minimum Spanning Tree algorithm to find the ML and MAP mixture of trees for a variety of priors, including the Dirichlet and the MDL priors.

59 citations


Proceedings Article
01 Feb 1997

32 citations



Proceedings Article
01 Dec 1997
TL;DR: It is found that speakers learn to adjust their production of a vowel to compensate for feedback alterations that change the vowel's perceived phonetic identity; the effect generalizes across consonant contexts and to different vowels.
Abstract: Human subjects are known to adapt their motor behavior to a shift of the visual field brought about by wearing prism glasses over their eyes. We have studied the analog of this effect in speech. Using a device that can feedback transformed speech signals in real time, we exposed subjects to alterations of their own speech feedback. We found that speakers learn to adjust their production of a vowel to compensate for feedback alterations that change the vowel's perceived phonetic identity; moreover, the effect generalizes across consonant contexts and to different vowels.

Book
13 Nov 1997
TL;DR: The philosophy of animism is also related to the beliefs of the ancient Bon religion of Tibet and the Wu priesthood of China, as well as to primitive Shinto belief, strands of which are still evident in modern Japan as discussed by the authors.
Abstract: INTRODUCTION The philosophies of the east have arisen, not unlike those of the occidental cultures, from a host of different influences and over a vast time-span that reaches back to the misty edge of prehistory. Beliefs of tremendous antiquity have been evidenced through archaeological discoveries spanning the regions of the globe from India to Japan. Some were clearly carried eastwards from the Cradle of Civilization in Mesopotamia whilst others can only have been derived independently, the product of more local minds and inspiration. In each case it is possible to detect beliefs and understandings of the world around us that have been part of a common frame existing virtually everywhere on the planet. These beliefs are represented in the tribal shamanism of nomadic hunting cultures and the philosophy of animism from which it derives. They can be discerned in the Vedic scriptures which form the bedrock of Hinduism, in the ancient Bon religion of Tibet and the archaic Wu priesthood of China, as well as in aspects of primitive Shinto belief, strands of which are still evident in modern Japan. Yet out of this common mould arose philosophies that are peculiar to the eastern mind and its attitude concerning life and death. It is almost inconceivable that a Gautama Buddha, a Lao Tzu, the founder of Chinese Tao ism, a Confucius, or a Hui Neng, the sixth Chinese Patriarch who gave the oriental world the concept of Zen, would have arisen in the western hemisphere. Most of the philosophies of the east not only claim great antiquity but also exert dynamic influences on modern life. Hinduism and Buddhism are a veritable part of the everyday round of living and dying amongst vast millions in the Indian subcontinent and much of South-East Asia. In Japan and Korea religious observances are an essential prerequisite to many of the activities of the secular world. This was also true in China until such traditions were driven out by the impositions of Communism, but these deep-rooted instincts may yet stage their come back as liberalization proceeds. One of the keys to the success and remarkable tenacity of the eastern philosophies has been the ability to adapt, to compromise, and to meld comfortably with the beliefs of others. Many of the older faiths, whose appeal was in danger of becoming passe, embraced Buddhism and Confucianism, the great driving forces of missionary zeal in the eastern hemisphere. They achieved this symbiosis unfettered by the restraint that has too often punished Judaism, Christianity and Islam, the great bastions of monotheism. It is these distinctions, in part, which stimulate us in the west with such a fascination and curiosity about the wisdom of the east, not so much alien as quintessentially exotic.