Impedance control and internal model use during the initial stage of adaptation to novel dynamics in humans.

This study investigated the neuromuscular mechanisms underlying the initial stage of adaptation to novel dynamics. A destabilizing velocity-dependent force field (VF) was introduced for sets of three consecutive trials. Between sets a random number of 4-8 null field trials were interposed, where the VF was inactivated. This prevented subjects from learning the novel dynamics, making it possible to repeatedly recreate the initial adaptive response. We were able to investigate detailed changes in neural control between the first, second and third VF trials. We identified two feedforward control mechanisms, which were initiated on the second VF trial and resulted in a 50% reduction in the hand path error. Responses to disturbances encountered on the first VF trial were feedback in nature, i.e. reflexes and voluntary correction of errors. However, on the second VF trial, muscle activation patterns were modified in anticipation of the effects of the force field. Feedforward cocontraction of all muscles was used to increase the viscoelastic impedance of the arm. While stiffening the arm, subjects also exerted a lateral force to counteract the perturbing effect of the force field. These anticipatory actions indicate that the central nervous system responds rapidly to counteract hitherto unfamiliar disturbances by a combination of increased viscoelastic impedance and formation of a crude internal dynamics model.

Facilitation of learning induced by both random and gradual visuomotor task variation.

Motor task variation has been shown to be a key ingredient in skill transfer, retention, and structural learning. However, many studies only compare training of randomly varying tasks to either blocked or null training, and it is not clear how experiencing different nonrandom temporal orderings of tasks might affect the learning process. Here we study learning in human subjects who experience the same set of visuomotor rotations, evenly spaced between -60° and +60°, either in a random order or in an order in which the rotation angle changed gradually. We compared subsequent learning of three test blocks of +30°→-30°→+30° rotations. The groups that underwent either random or gradual training showed significant (P < 0.01) facilitation of learning in the test blocks compared with a control group who had not experienced any visuomotor rotations before. We also found that movement initiation times in the random group during the test blocks were significantly (P < 0.05) lower than for the gradual or the control group. When we fit a state-space model with fast and slow learning processes to our data, we found that the differences in performance in the test block were consistent with the gradual or random task variation changing the learning and retention rates of only the fast learning process. Such adaptation of learning rates may be a key feature of ongoing meta-learning processes. Our results therefore suggest that both gradual and random task variation can induce meta-learning and that random learning has an advantage in terms of shorter initiation times, suggesting less reliance on cognitive processes.

Derivation of a vector model for a Brushless Doubly-Fed Machine with multiple loops per nest

The paper presents a vector model for a Brushless Doubly-Fed Machine (BDFM). The BDFM has 4 and 8 pole stator windings and a nested-loop rotor cage. The rotor cage has six nests equally spaced around the circumference and each nest comprises three loops. All the rotor loops are short circuited via a common end-ring at one end. The vector model is derived based on the electrical equations of the machine and appropriate vector transformations. In contrast to the stator, there is no three phase circuit in the rotor. Therefore, the vector transformations suitable for three phase circuits can not be utilised for the rotor circuit. A new vector transformation is employed for the rotor circuit quantities. The approach presented in this paper can be extended for a BDFM with any stator poles combination and any number of loops per nest. Simulation results from the model implemented in Simulink are presented. © 2008 IEEE.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

Phrase-based statistical language generation using graphical models and active learning

Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to inform the generation decision process. Both approaches rely on the existence of a handcrafted generator, which limits their scalability to new domains. This paper presents BAGEL, a statistical language generator which uses dynamic Bayesian networks to learn from semantically-aligned data produced by 42 untrained annotators. A human evaluation shows that BAGEL can generate natural and informative utterances from unseen inputs in the information presentation domain. Additionally, generation performance on sparse datasets is improved significantly by using certainty-based active learning, yielding ratings close to the human gold standard with a fraction of the data. © 2010 Association for Computational Linguistics.

State-space inference and learning with Gaussian processes

State-space inference and learning with Gaussian processes (GPs) is an unsolved problem. We propose a new, general methodology for inference and learning in nonlinear state-space models that are described probabilistically by non-parametric GP models. We apply the expectation maximization algorithm to iterate between inference in the latent state-space and learning the parameters of the underlying GP dynamics model. Copyright 2010 by the authors.

An Infinite Latent Attribute Model for Network Data

Latent variable models for network data extract a summary of the relational structure underlying an observed network. The simplest possible models subdivide nodes of the network into clusters; the probability of a link between any two nodes then depends only on their cluster assignment. Currently available models can be classified by whether clusters are disjoint or are allowed to overlap. These models can explain a "flat" clustering structure. Hierarchical Bayesian models provide a natural approach to capture more complex dependencies. We propose a model in which objects are characterised by a latent feature vector. Each feature is itself partitioned into disjoint groups (subclusters), corresponding to a second layer of hierarchy. In experimental comparisons, the model achieves significantly improved predictive performance on social and biological link prediction tasks. The results indicate that models with a single layer hierarchy over-simplify real networks.

A Structured Model of Video Reproduces Primary Visual Cortical Organisation

The visual system must learn to infer the presence of objects and features in the world from the images it encounters, and as such it must, either implicitly or explicitly, model the way these elements interact to create the image. Do the response properties of cells in the mammalian visual system reflect this constraint? To address this question, we constructed a probabilistic model in which the identity and attributes of simple visual elements were represented explicitly and learnt the parameters of this model from unparsed, natural video sequences. After learning, the behaviour and grouping of variables in the probabilistic model corresponded closely to functional and anatomical properties of simple and complex cells in the primary visual cortex (V1). In particular, feature identity variables were activated in a way that resembled the activity of complex cells, while feature attribute variables responded much like simple cells. Furthermore, the grouping of the attributes within the model closely parallelled the reported anatomical grouping of simple cells in cat V1. Thus, this generative model makes explicit an interpretation of complex and simple cells as elements in the segmentation of a visual scene into basic independent features, along with a parametrisation of their moment-by-moment appearances. We speculate that such a segmentation may form the initial stage of a hierarchical system that progressively separates the identity and appearance of more articulated visual elements, culminating in view-invariant object recognition.

Modelling and control of nonlinear systems using Gaussian processes with partial model information

Gaussian processes are gaining increasing popularity among the control community, in particular for the modelling of discrete time state space systems. However, it has not been clear how to incorporate model information, in the form of known state relationships, when using a Gaussian process as a predictive model. An obvious example of known prior information is position and velocity related states. Incorporation of such information would be beneficial both computationally and for faster dynamics learning. This paper introduces a method of achieving this, yielding faster dynamics learning and a reduction in computational effort from O(Dn2) to O((D - F)n2) in the prediction stage for a system with D states, F known state relationships and n observations. The effectiveness of the method is demonstrated through its inclusion in the PILCO learning algorithm with application to the swing-up and balance of a torque-limited pendulum and the balancing of a robotic unicycle in simulation. © 2012 IEEE.

Learning based automatic face annotation for arbitrary poses and expressions from frontal images only

Statistical approaches for building non-rigid deformable models, such as the Active Appearance Model (AAM), have enjoyed great popularity in recent years, but typically require tedious manual annotation of training images. In this paper, a learning based approach for the automatic annotation of visually deformable objects from a single annotated frontal image is presented and demonstrated on the example of automatically annotating face images that can be used for building AAMs for fitting and tracking. This approach employs the idea of initially learning the correspondences between landmarks in a frontal image and a set of training images with a face in arbitrary poses. Using this learner, virtual images of unseen faces at any arbitrary pose for which the learner was trained can be reconstructed by predicting the new landmark locations and warping the texture from the frontal image. View-based AAMs are then built from the virtual images and used for automatically annotating unseen images, including images of different facial expressions, at any random pose within the maximum range spanned by the virtually reconstructed images. The approach is experimentally validated by automatically annotating face images from three different databases. © 2009 IEEE.

Dopamine and performance in a reinforcement learning task: evidence from Parkinson's disease.

The role dopamine plays in decision-making has important theoretical, empirical and clinical implications. Here, we examined its precise contribution by exploiting the lesion deficit model afforded by Parkinson's disease. We studied patients in a two-stage reinforcement learning task, while they were ON and OFF dopamine replacement medication. Contrary to expectation, we found that dopaminergic drug state (ON or OFF) did not impact learning. Instead, the critical factor was drug state during the performance phase, with patients ON medication choosing correctly significantly more frequently than those OFF medication. This effect was independent of drug state during initial learning and appears to reflect a facilitation of generalization for learnt information. This inference is bolstered by our observation that neural activity in nucleus accumbens and ventromedial prefrontal cortex, measured during simultaneously acquired functional magnetic resonance imaging, represented learnt stimulus values during performance. This effect was expressed solely during the ON state with activity in these regions correlating with better performance. Our data indicate that dopamine modulation of nucleus accumbens and ventromedial prefrontal cortex exerts a specific effect on choice behaviour distinct from pure learning. The findings are in keeping with the substantial other evidence that certain aspects of learning are unaffected by dopamine lesions or depletion, and that dopamine plays a key role in performance that may be distinct from its role in learning.

Model-based influences on humans' choices and striatal prediction errors.

The mesostriatal dopamine system is prominently implicated in model-free reinforcement learning, with fMRI BOLD signals in ventral striatum notably covarying with model-free prediction errors. However, latent learning and devaluation studies show that behavior also shows hallmarks of model-based planning, and the interaction between model-based and model-free values, prediction errors, and preferences is underexplored. We designed a multistep decision task in which model-based and model-free influences on human choice behavior could be distinguished. By showing that choices reflected both influences we could then test the purity of the ventral striatal BOLD signal as a model-free report. Contrary to expectations, the signal reflected both model-free and model-based predictions in proportions matching those that best explained choice behavior. These results challenge the notion of a separate model-free learner and suggest a more integrated computational architecture for high-level human decision-making.

Dopamine and performance in a reinforcement learning task: Evidence from Parkinson's disease

The role dopamine plays in decision-making has important theoretical, empirical and clinical implications. Here, we examined its precise contribution by exploiting the lesion deficit model afforded by Parkinson's disease. We studied patients in a two-stage reinforcement learning task, while they were ON and OFF dopamine replacement medication. Contrary to expectation, we found that dopaminergic drug state (ON or OFF) did not impact learning. Instead, the critical factor was drug state during the performance phase, with patients ON medication choosing correctly significantly more frequently than those OFF medication. This effect was independent of drug state during initial learning and appears to reflect a facilitation of generalization for learnt information. This inference is bolstered by our observation that neural activity in nucleus accumbens and ventromedial prefrontal cortex, measured during simultaneously acquired functional magnetic resonance imaging, represented learnt stimulus values during performance. This effect was expressed solely during the ON state with activity in these regions correlating with better performance. Our data indicate that dopamine modulation of nucleus accumbens and ventromedial prefrontal cortex exerts a specific effect on choice behaviour distinct from pure learning. The findings are in keeping with the substantial other evidence that certain aspects of learning are unaffected by dopamine lesions or depletion, and that dopamine plays a key role in performance that may be distinct from its role in learning. © 2012 The Author.

Reinforcement learning using a continuous time actor-critic framework with spiking neurons.

Animals repeat rewarded behaviors, but the physiological basis of reward-based learning has only been partially elucidated. On one hand, experimental evidence shows that the neuromodulator dopamine carries information about rewards and affects synaptic plasticity. On the other hand, the theory of reinforcement learning provides a framework for reward-based learning. Recent models of reward-modulated spike-timing-dependent plasticity have made first steps towards bridging the gap between the two approaches, but faced two problems. First, reinforcement learning is typically formulated in a discrete framework, ill-adapted to the description of natural situations. Second, biologically plausible models of reward-modulated spike-timing-dependent plasticity require precise calculation of the reward prediction error, yet it remains to be shown how this can be computed by neurons. Here we propose a solution to these problems by extending the continuous temporal difference (TD) learning of Doya (2000) to the case of spiking neurons in an actor-critic network operating in continuous time, and with continuous state and action representations. In our model, the critic learns to predict expected future rewards in real time. Its activity, together with actual rewards, conditions the delivery of a neuromodulatory TD signal to itself and to the actor, which is responsible for action choice. In simulations, we show that such an architecture can solve a Morris water-maze-like navigation task, in a number of trials consistent with reported animal performance. We also use our model to solve the acrobot and the cartpole problems, two complex motor control tasks. Our model provides a plausible way of computing reward prediction error in the brain. Moreover, the analytically derived learning rule is consistent with experimental evidence for dopamine-modulated spike-timing-dependent plasticity.