Structure learning in action.

'Learning to learn' phenomena have been widely investigated in cognition, perception and more recently also in action. During concept learning tasks, for example, it has been suggested that characteristic features are abstracted from a set of examples with the consequence that learning of similar tasks is facilitated-a process termed 'learning to learn'. From a computational point of view such an extraction of invariants can be regarded as learning of an underlying structure. Here we review the evidence for structure learning as a 'learning to learn' mechanism, especially in sensorimotor control where the motor system has to adapt to variable environments. We review studies demonstrating that common features of variable environments are extracted during sensorimotor learning and exploited for efficient adaptation in novel tasks. We conclude that structure learning plays a fundamental role in skill learning and may underlie the unsurpassed flexibility and adaptability of the motor system.

From subspace learning to distance learning: A geometrical optimization approach

In this paper, we adopt a differential-geometry viewpoint to tackle the problem of learning a distance online. As this problem can be cast into the estimation of a fixed-rank positive semidefinite (PSD) matrix, we develop algorithms that exploits the rich geometry structure of the set of fixed-rank PSD matrices. We propose a method which separately updates the subspace of the matrix and its projection onto that subspace. A proper weighting of the two iterations enables to continuously interpolate between the problem of learning a subspace and learning a distance when the subspace is fixed. © 2009 IEEE.

Structure learning in a sensorimotor association task.

Learning is often understood as an organism's gradual acquisition of the association between a given sensory stimulus and the correct motor response. Mathematically, this corresponds to regressing a mapping between the set of observations and the set of actions. Recently, however, it has been shown both in cognitive and motor neuroscience that humans are not only able to learn particular stimulus-response mappings, but are also able to extract abstract structural invariants that facilitate generalization to novel tasks. Here we show how such structure learning can enhance facilitation in a sensorimotor association task performed by human subjects. Using regression and reinforcement learning models we show that the observed facilitation cannot be explained by these basic models of learning stimulus-response associations. We show, however, that the observed data can be explained by a hierarchical Bayesian model that performs structure learning. In line with previous results from cognitive tasks, this suggests that hierarchical Bayesian inference might provide a common framework to explain both the learning of specific stimulus-response associations and the learning of abstract structures that are shared by different task environments.

Composition and decomposition in bimanual dynamic learning.

Our ability to skillfully manipulate an object often involves the motor system learning to compensate for the dynamics of the object. When the two arms learn to manipulate a single object they can act cooperatively, whereas when they manipulate separate objects they control each object independently. We examined how learning transfers between these two bimanual contexts by applying force fields to the arms. In a coupled context, a single dynamic is shared between the arms, and in an uncoupled context separate dynamics are experienced independently by each arm. In a composition experiment, we found that when subjects had learned uncoupled force fields they were able to transfer to a coupled field that was the sum of the two fields. However, the contribution of each arm repartitioned over time so that, when they returned to the uncoupled fields, the error initially increased but rapidly reverted to the previous level. In a decomposition experiment, after subjects learned a coupled field, their error increased when exposed to uncoupled fields that were orthogonal components of the coupled field. However, when the coupled field was reintroduced, subjects rapidly readapted. These results suggest that the representations of dynamics for uncoupled and coupled contexts are partially independent. We found additional support for this hypothesis by showing significant learning of opposing curl fields when the context, coupled versus uncoupled, was alternated with the curl field direction. These results suggest that the motor system is able to use partially separate representations for dynamics of the two arms acting on a single object and two arms acting on separate objects.

Parameter learning for POMDP spoken dialogue models

The partially observable Markov decision process (POMDP) provides a popular framework for modelling spoken dialogue. This paper describes how the expectation propagation algorithm (EP) can be used to learn the parameters of the POMDP user model. Various special probability factors applicable to this task are presented, which allow the parameters be to learned when the structure of the dialogue is complex. No annotations, neither the true dialogue state nor the true semantics of user utterances, are required. Parameters optimised using the proposed techniques are shown to improve the performance of both offline transcription experiments as well as simulated dialogue management performance. ©2010 IEEE.

Adaptation to stable and unstable dynamics achieved by combined impedance control and inverse dynamics model.

This study compared adaptation in novel force fields where trajectories were initially either stable or unstable to elucidate the processes of learning novel skills and adapting to new environments. Subjects learned to move in a null force field (NF), which was unexpectedly changed either to a velocity-dependent force field (VF), which resulted in perturbed but stable hand trajectories, or a position-dependent divergent force field (DF), which resulted in unstable trajectories. With practice, subjects learned to compensate for the perturbations produced by both force fields. Adaptation was characterized by an initial increase in the activation of all muscles followed by a gradual reduction. The time course of the increase in activation was correlated with a reduction in hand-path error for the DF but not for the VF. Adaptation to the VF could have been achieved solely by formation of an inverse dynamics model and adaptation to the DF solely by impedance control. However, indices of learning, such as hand-path error, joint torque, and electromyographic activation and deactivation suggest that the CNS combined these processes during adaptation to both force fields. Our results suggest that during the early phase of learning there is an increase in endpoint stiffness that serves to reduce hand-path error and provides additional stability, regardless of whether the dynamics are stable or unstable. We suggest that the motor control system utilizes an inverse dynamics model to learn the mean dynamics and an impedance controller to assist in the formation of the inverse dynamics model and to generate needed stability.

Impedance control is tuned to multiple directions of movement

Humans are able to learn tool-handling tasks, such as carving, demonstrating their competency to make and vary the direction of movements in unstable environments. It has been shown that when a single reaching movement is repeated in unstable dynamics, the central nervous system (CNS) learns an impedance internal model to compensate for the environment instability. However, there is still no explanation for how humans can learn to move in various directions in such environments. In this study, we investigated whether and how humans compensate for instability while learning two different reaching movements simultaneously. Results show that when performing movements in two different directions, separated by a 35° angle, the CNS was able to compensate for the unstable dynamics. After adaptation, the force was found to be similar to the free movement condition, but stiffness increased in the direction of instability, specifically for each direction of movement. Our findings suggest that the CNS either learned an internal model generalizing over different movements, or alternatively that it was able to switch between specific models acquired simultaneously. © 2008 IEEE.

Single trial learning of external dynamics: What can the brain teach us about learning mechanisms?

Humans have exceptional abilities to learn new skills, manipulate tools and objects, and interact with our environment. In order to be successful at these tasks, our brain has developed learning mechanisms to deal with and compensate for the constantly changing dynamics of the world. If this mechanism or mechanisms can be understood from a computational point of view, then they can also be used to drive the adaptability and learning of robots. In this paper, we will present a new technique for examining changes in the feedforward motor command due to adaptation. This technique can then be utilized for examining motor adaptation in humans and determining a computational algorithm which explains motor learning. © 2007.

Learning the dynamics of the external world: Brain inspired learning for robotic applications

Humans have exceptional abilities to learn new skills, manipulate tools and objects, and interact with our environment. In order to be successful at these tasks, our brain has become exceptionally well adapted to learning to deal not only with the complex dynamics of our own limbs but also with novel dynamics in the external world. While learning of these dynamics includes learning the complex time-varying forces at the end of limbs through the updating of internal models, it must also include learning the appropriate mechanical impedance in order to stabilize both the limb and any objects contacted in the environment. This article reviews the field of human learning by examining recent experimental evidence about adaptation to novel unstable dynamics and explores how this knowledge about the brain and neuro-muscular system can expand the learning capabilities of robotics and prosthetics. © 2006.

Impedance control is selectively tuned to multiple directions of movement

Humans are able to learn tool-handling tasks, such as carving, demonstrating their competency to make movements in unstable environments with varied directions. When faced with a single direction of instability, humans learn to selectively co-contract their arm muscles tuning the mechanical stiffness of the limb end point to stabilize movements. This study examines, for the first time, subjects simultaneously adapting to two distinct directions of instability, a situation that may typically occur when using tools. Subjects learned to perform reaching movements in two directions, each of which had lateral instability requiring control of impedance. The subjects were able to adapt to these unstable interactions and switch between movements in the two directions; they did so by learning to selectively control the end-point stiffness counteracting the environmental instability without superfluous stiffness in other directions. This finding demonstrates that the central nervous system can simultaneously tune the mechanical impedance of the limbs to multiple movements by learning movement-specific solutions. Furthermore, it suggests that the impedance controller learns as a function of the state of the arm rather than a general strategy. © 2011 the American Physiological Society.

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.

Generalization in Adaptation to Stable and Unstable Dynamics

Humans skillfully manipulate objects and tools despite the inherent instability. In order to succeed at these tasks, the sensorimotor control system must build an internal representation of both the force and mechanical impedance. As it is not practical to either learn or store motor commands for every possible future action, the sensorimotor control system generalizes a control strategy for a range of movements based on learning performed over a set of movements. Here, we introduce a computational model for this learning and generalization, which specifies how to learn feedforward muscle activity in a function of the state space. Specifically, by incorporating co-activation as a function of error into the feedback command, we are able to derive an algorithm from a gradient descent minimization of motion error and effort, subject to maintaining a stability margin. This algorithm can be used to learn to coordinate any of a variety of motor primitives such as force fields, muscle synergies, physical models or artificial neural networks. This model for human learning and generalization is able to adapt to both stable and unstable dynamics, and provides a controller for generating efficient adaptive motor behavior in robots. Simulation results exhibit predictions consistent with all experiments on learning of novel dynamics requiring adaptation of force and impedance, and enable us to re-examine some of the previous interpretations of experiments on generalization. © 2012 Kadiallah et al.