Accelerated learning by active example selection

Let the force guide you: a performance-based adaptive algorithm for postural training using haptic feedback

Motor learning is an essential component of human behavior. Many different factors can influence the process of motor learning, such as the amount of practice and type of feedback. Changes in task difficulty during training can also considerably impact motor learning. Typical motor learning studies include a sequential variation of task difficulty, i.e., easy to challenging, irrespective of user performance. However, many studies have reported the importance of performance-based task difficulty variation for effective motor learning and skill transfer. A performance-based adaptive algorithm for task difficulty variation based on the challenge-point framework is proposed in this study. The algorithm is described for postural adaptation during simultaneous upper-limb training. Ten healthy participants (28 ± 2.44 years) were recruited to validate the algorithm. Participants adapted to a postural target of 20° in the anterior direction from the initial upright posture while performing a unimanual reaching task using a robotic device. Results suggest a significant decrease in postural error after training. The algorithm successfully adapted the task difficulty based on the performance of the user. The proposed algorithm could be modified for different motor skills and can be further evaluated for different applications in order to maximize the potential benefits of rehabilitation sessions.

A dynamically adjusted mixed emphasis method for building boosting ensembles

Progressively emphasizing samples that are difficult to classify correctly is the base for the recognized high performance of real Adaboost (RA) ensembles. The corresponding emphasis function can be written as a product of a factor that measures the quadratic error and a factor related to the proximity to the classification border; this fact opens the door to explore the potential advantages provided by using adjustable combined forms of these factors. In this paper, we introduce a principled procedure to select the combination parameter each time a new learner is added to the ensemble, just by maximizing the associated edge parameter, calling the resulting method the dynamically adapted weighted emphasis RA (DW-RA). A number of application examples illustrates the performance improvements obtained by DW-RA.

The emergence of goals in a self-organizing network: a non-mentalist model of intentional actions

A model of intentional actions is presented through the operation of two connected neural networks. A deterministic causal recurrent network relates a random initial state to an ordered final state. A perceptron-like, feed-forward network provides a memory mechanism that links the final states to the original initial states. A non-supervised learning mechanism that selects which final states are defined as goals to be retrieved together with initial states leading to them. Causal sequences of states are transformed into procedures directed towards the achievements of goals. We propose a mechanism through which goals and their achievement in goal-directed actions can be emerging properties of self-organizing networks, not initially endowed with intentionality. This allows for a monist, non-mentalist description which does not need to resort to intentional mental states as causes of intentional actions. Cognitive, neurophysiological and philosophical implications are discussed.