Showing papers by "Michael I. Jordan published in 1995"

An Internal Model for Sensorimotor Integration

Abstract: On the basis of computational studies it has been proposed that the central nervous system internally simulates the dynamic behavior of the motor system in planning, control, and learning; the existence and use of such an internal model is still under debate. A sensorimotor integration task was investigated in which participants estimated the location of one of their hands at the end of movements made in the dark and under externally imposed forces. The temporal propagation of errors in this task was analyzed within the theoretical framework of optimal state estimation. These results provide direct support for the existence of an internal model.

Forward models: supervised learning with a distal teacher

Abstract: Internal models of the environment have an important role to play in adaptive systems, in general, and are of particular importance for the supervised learning paradigm. In this article we demonstrate that certain classical problems associated with the notion of the “teacher” in supervised learning can be solved by judicious use of learned internal models as components of the adaptive system. In particular, we show how supervised learning algorithms can be utilized in cases in which an unknown dynamical system intervenes between actions and desired outcomes. Our approach applies to any supervised learning algorithm that is capable of learning in multilayer networks.

Factorial Hidden Markov Models

Abstract: Hidden Markov models (HMMs) have proven to be one of the most widely used tools for learning probabilistic models of time series data. In an HMM, information about the past is conveyed through a single discrete variable—the hidden state. We discuss a generalization of HMMs in which this state is factored into multiple state variables and is therefore represented in a distributed manner. We describe an exact algorithm for inferring the posterior probabilities of the hidden state variables given the observations, and relate it to the forward–backward algorithm for HMMs and to algorithms for more general graphical models. Due to the combinatorial nature of the hidden state representation, this exact algorithm is intractable. As in other intractable systems, approximate inference can be carried out using Gibbs sampling or variational methods. Within the variational framework, we present a structured approximation in which the the state variables are decoupled, yielding a tractable algorithm for learning the parameters of the model. Empirical comparisons suggest that these approximations are efficient and provide accurate alternatives to the exact methods. Finally, we use the structured approximation to model Bach‘s chorales and show that factorial HMMs can capture statistical structure in this data set which an unconstrained HMM cannot.

Are arm trajectories planned in kinematic or dynamic coordinates? An adaptation study

Abstract: There are several invariant features of pointto-point human arm movements: trajectories tend to be straight, smooth, and have bell-shaped velocity profiles. One approach to accounting for these data is via optimization theory; a movement is specified implicitly as the optimum of a cost function, e.g., integrated jerk or torque change. Optimization models of trajectory planning, as well as models not phrased in the optimization framework, generally fall into two main groups-those specified in kinematic coordinates and those specified in dynamic coordinates. To distinguish between these two possibilities we have studied the effects of artificial visual feedback on planar two-joint arm movements. During self-paced point-to-point arm movements the visual feedback of hand position was altered so as to increase the perceived curvature of the movement. The perturbation was zero at both ends of the movement and reached a maximum at the midpoint of the movement. Cost functions specified by hand coordinate kinematics predict adaptation to increased curvature so as to reduce the visual curvature, while dynamically specified cost functions predict no adaptation in the underlying trajectory planner, provided the final goal of the movement can still be achieved. We also studied the effects of reducing the perceived curvature in transverse movements, which are normally slightly curved. Adaptation should be seen in this condition only if the desired trajectory is both specified in kinematic coordinates and actually curved. Increasing the perceived curvature of normally straight sagittal movements led to significant (P 0.05). The results of the curvature-increasing study suggest that trajectories are planned in visually based kinematic coordinates. The results of the curvature-reducing study suggest that the desired trajectory is straight in visual space. These results are incompatible with purely dynamicbased models such as the minimum torque change model. We suggest that spatial perception-as mediated by vision-plays a fundamental role in trajectory planning.

Exploiting Tractable Substructures in Intractable Networks

Abstract: We develop a refined mean field approximation for inference and learning in probabilistic neural networks. Our mean field theory, unlike most, does not assume that the units behave as independent degrees of freedom; instead, it exploits in a principled way the existence of large substructures that are computationally tractable. To illustrate the advantages of this framework, we show how to incorporate weak higher order interactions into a first-order hidden Markov model, treating the corrections (but not the first order structure) within mean field theory.

The encyclopedia of fungi of Britain and Europe

Abstract: The biology of fungi nomenclature and systematics foraying and conservation chemical tests photography Ascomycetes - cup fungi, Morels and Helvellas, truffles, others Homobasidiomycetes - fairy clubs, chanterelles, tooth fungi, encrusting forms and other brackets, agaricales, cortinariales, russulales, boletales, gastromycetes (puff balls etc) heterobasidiomycetes myxomycetes (limited examples).

The Organization of Action Sequences: Evidence From a Relearning Task.

Abstract: In two studies, the organization of sequential behavior in transcription typing was investigated. The design of the studies made it possible to test the hypothesis that sequential skill in typing resides only at an abstract, effector-independent level. Skilled typists (N = 12) learned to type on an altered keyboard in an experimental paradigm that allowed only certain components of the motor control system to adapt to the alterations. When performance was compared on a pretest and a posttest, various decrements in the typists' speed and accuracy were observed. The forms of these decrements provided evidence against a strong form of the effector-independent hypothesis.

Learning Fine Motion by Markov Mixtures of Experts

Abstract: Compliant control is a standard method for performing fine manipulation tasks, like grasping and assembly, but it requires estimation of the state of contact between the robot arm and the objects involved. Here we present a method to learn a model of the movement from measured data. The method requires little or no prior knowledge and the resulting model explicitly estimates the state of contact. The current state of contact is viewed as the hidden state variable of a discrete HMM. The control dependent transition probabilities between states are modeled as parametrized functions of the measurement We show that their parameters can be estimated from measurements concurrently with the estimation of the parameters of the movement in each state of contact. The learning algorithm is a variant of the EM procedure. The E step is computed exactly; solving the M step exactly would require solving a set of coupled nonlinear algebraic equations in the parameters. Instead, gradient ascent is used to produce an increase in likelihood.

Reinforcement Learning by Probability Matching

Abstract: We present a new algorithm for associative reinforcement learning. The algorithm is based upon the idea of matching a network's output probability with a probability distribution derived from the environment's reward signal. This Probability Matching algorithm is shown to perform faster and be less susceptible to local minima than previously existing algorithms. We use Probability Matching to train mixture of experts networks, an architecture for which other reinforcement learning rules fail to converge reliably on even simple problems. This architecture is particularly well suited for our algorithm as it can compute arbitrarily complex functions yet calculation of the output probability is simple.

Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks

Abstract: Sigmoid type belief networks, a class of probabilistic neural networks, provide a natural framework for compactly representing probabilistic information in a variety of unsupervised and supervised learning problems. Often the parameters used in these networks need to be learned from examples. Unfortunately, estimating the parameters via exact probabilistic calculations (i.e, the EM-algorithm) is intractable even for networks with fairly small numbers of hidden units. We propose to avoid the infeasibility of the E step by bounding likelihoods instead of computing them exactly. We introduce extended and complementary representations for these networks and show that the estimation of the network parameters can be made fast (reduced to quadratic optimization) by performing the estimation in either of the alternative domains. The complementary networks can be used for continuous density estimation as well.

Adaptation in speech production to transformed auditory feedback

Abstract: This study investigated the ability of the speech production system to learn to compensate for changes in auditory feedback. The setup used for this was a DSP system that transformed the immediate feedback a subject received when speaking. This system can analyze a subject’s speech into a formantlike representation, possibly alter it, and then use it to resynthesize speech which is fed back to the subject with no noticeable delay (16 ms). The first of the experiments investigated whether subjects would learn to compensate for a change in vowel identity when producing CVC words. It was found that compensatory articulations were indeed learned, and that these persisted even when no auditory feedback was provided. The findings suggest similarities between speech and other sensorimotor tasks, such as reaching, which also show such adaptation. Other experiments characterizing the degree to which this effect generalizes across differing word and vowel environments will also be presented.