Task-specific Functions Research Articles

A Kernel-Based Approach for Biomedical Named Entity Recognition

Support vector machine (SVM) is one of the popular machine learning techniques used in various text processing tasks including named entity recognition (NER). The performance of the SVM classifier largely depends on the appropriateness of the kernel function. In the last few years a number of task-specific kernel functions have been proposed and used in various text processing tasks, for example, string kernel, graph kernel, tree kernel and so on. So far very few efforts have been devoted to the development of NER task specific kernel. In the literature we found that the tree kernel has been used in NER task only for entity boundary detection or reannotation. The conventional tree kernel is unable to execute the complete NER task on its own. In this paper we have proposed a kernel function, motivated by the tree kernel, which is able to perform the complete NER task. To examine the effectiveness of the proposed kernel, we have applied the kernel function on the openly available JNLPBA 2004 data. Our kernel executes the complete NER task and achieves reasonable accuracy.

TASK-ORIENTED PROBABILISTIC ACTIVE VISION

In this work, an explicitly task-oriented approach to the active vision problem is presented. The system tries to reduce the most relevant components of the uncertainty in the world model, for the task the robot is currently performing. It is task oriented in the sense that it explicitly considers a task-specific value function. As test-bed for the presented active vision approach, we selected a robot soccer attention problem: goal-covering by a goalie player. The proposed system is compared with information-based approaches. Experimental results show that it surpasses them in the tested application. We conclude that, when the goal is not the uncertainty reduction itself, the minimization of the belief entropy is not a useful optimality criterion, and that for such cases, task-oriented optimality criteria are better suited.

Convex multi-task feature learning

We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single-task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across-tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select—not learn—a few common variables across the tasks.

Muscle activation in coupled scapulohumeral motions in the high performance tennis serve

Objective:To evaluate muscle activation patterns in selected scapulohumeral muscles in the tennis serve. These patterns of muscle activation have not been evaluated in other studies of the tennis serve. Fine...

Functional morphology of proximal hindlimb muscles in the frogRana pipiens

Musculoskeletal models have become important tools in understanding motor control issues ranging from how muscles power movement to how sensory feedback supports movements. In the present study, we developed the initial musculotendon subsystem of a realistic model of the frog Rana pipiens. We measured the anatomical properties of 13 proximal muscles in the frog hindlimb and incorporated these measurements into a set of musculotendon actuators. We examined whether the interaction between this musculotendon subsystem and a previously developed skeleton/joint subsystem captured the passive behavior of the real frog's musculoskeletal system. To do this, we compared the moment arms of musculotendon complexes measured experimentally with moment arms predicted by the model. We also compared sarcomere lengths measured experimentally at the starting and take-off positions of a jump with sarcomere lengths predicted by the model at these same limb positions. On the basis of the good fit of the experimental data, we used the model to describe the multi-joint mechanical effects produced by contraction of each hindlimb muscle and to predict muscle trajectories during a range of limb behaviors (wiping, defensive kicking, swimming and jumping). Through these analyses, we show that all hindlimb muscles have multiple functions with respect to accelerating the limb in its three-dimensional workspace and that the balance of functions depends greatly on limb configuration. In addition, we show that muscles have multiple, task-specific functions with respect to the type of contraction performed. The results of this study provide important data regarding the multifunctional role of hindlimb muscles in the frog and form a foundation upon which additional model subsystems (e.g. neural) and more sophisticated muscle models can be appended.