Learning Task Knowledge

This work addresses the problem of knowledge distillation for deep face recognition task. Knowledge distillation technique is known to be an effective way of model compression, which implies transferring of the knowledge from high-capacity teacher to a lightweight student. The knowledge and the way how it is distilled can be defined in different ways depending on the problem where the technique is applied. Considering the fact that face recognition is a typical metric learning task, we propose to perform knowledge distillation on a score-level. Specifically, for any pair of matching scores computed by teacher, our method forces student to have the same order for the corresponding matching scores. We evaluate proposed pairwise ranking distillation (PWR) approach using several face recognition benchmarks for both face verification and face identification scenarios. Experimental results show that PWR not only can improve over the baseline method by a large margin, but also outperforms other score-level distillation approaches.

Download Full-text

Path Planning Based on Task Knowledge and User’s Intention

Journal of Robotics and Mechatronics ◽

10.20965/jrm.1996.p0025 ◽

1996 ◽

Vol 8 (1) ◽

pp. 25-32

Author(s):

Hiroyuki Ogata ◽

◽

Tomoichi Takahashi ◽

Keyword(s):

Path Planning ◽

Learning Task ◽

Complex Environments ◽

Heuristic Function ◽

A Algorithm ◽

Task Knowledge

This paper introduces a method to extract task knowledge from an example shown by an teacher or generated by a planner, and to apply the knowledge to plan a path in similar environments where dimentions, design and location of parts may change. Our goal is to make efficient use of learning task resource and to easily plan a path in complex environments. Our method is based on the A*algorithm. We developed a technique to generate a suboptimal path with much less search nodes than the traditional A*algorithm, and to make a heuristic function that includes task knowledge. Examples are shown to verify the effectiveness of our method.

Download Full-text

Learning Task Knowledge from Dialog and Web Access

Robotics ◽

10.3390/robotics4020223 ◽

2015 ◽

Vol 4 (2) ◽

pp. 223-252 ◽

Cited By ~ 8

Author(s):

Vittorio Perera ◽

Robin Soetens ◽

Thomas Kollar ◽

Mehdi Samadi ◽

Yichao Sun ◽

...

Keyword(s):

Learning Task ◽

Task Knowledge ◽

Web Access

Download Full-text

Epistemic and relational conflicts in sharing identical vs. complementary information during cooperative learning

Swiss Journal of Psychology ◽

10.1024//1421-0185.61.3.139 ◽

2002 ◽

Vol 61 (3) ◽

pp. 139-151 ◽

Cited By ~ 20

Author(s):

Céline Darnon ◽

Céline Buchs ◽

Fabrizio Butera

Keyword(s):

Cooperative Learning ◽

Social Comparison ◽

Positive Relationship ◽

Learning Task ◽

Control Group ◽

Complementary Information ◽

Relational Conflict ◽

The Social ◽

The University

When interacting on a learning task, which is typical of several academic situations, individuals may experience two different motives: Understanding the problem, or showing their competences. When a conflict (confrontation of divergent propositions) emerges from this interaction, it can be solved either in an epistemic way (focused on the task) or in a relational way (focused on the social comparison of competences). The latter is believed to be detrimental for learning. Moreover, research on cooperative learning shows that when they share identical information, partners are led to compare to each other, and are less encouraged to cooperate than when they share complementary information. An epistemic vs. relational conflict vs. no conflict was provoked in dyads composed by a participant and a confederate, working either on identical or on complementary information (N = 122). Results showed that, if relational and epistemic conflicts both entailed more perceived interactions and divergence than the control group, only relational conflict entailed more perceived comparison activities and a less positive relationship than the control group. Epistemic conflict resulted in a more positive perceived relationship than the control group. As far as performance is concerned, relational conflict led to a worse learning than epistemic conflict, and - after a delay - than the control group. An interaction between the two variables on delayed performance showed that epistemic and relational conflicts were different only when working with complementary information. This study shows the importance of the quality of relationship when sharing information during cooperative learning, a crucial factor to be taken into account when planning educational settings at the university.

Download Full-text

Blocking Is Sensitive to Causal Structure in 4-Year-Old and 8-Year-Old Children

Experimental Psychology (formerly Zeitschrift für Experimentelle Psychologie) ◽

10.1027/1618-3169.52.4.264 ◽

2005 ◽

Vol 52 (4) ◽

pp. 264-271 ◽

Cited By ~ 4

Author(s):

Tom Beckers ◽

Uschi Van den Broeck ◽

Marij Renne ◽

Stefaan Vandorpe ◽

Jan De Houwer ◽

...

Keyword(s):

Young Children ◽

Associative Learning ◽

Learning Theory ◽

Causal Structure ◽

Age Groups ◽

Learning Task ◽

Contingency Learning

Abstract. In a contingency learning task, 4-year-old and 8-year-old children had to predict the outcome displayed on the back of a card on the basis of cues presented on the front. The task was embedded in either a causal or a merely predictive scenario. Within this task, either a forward blocking or a backward blocking procedure was implemented. Blocking occurred in the causal but not in the predictive scenario. Moreover, blocking was affected by the scenario to the same extent in both age groups. The pattern of results was similar for forward and backward blocking. These results suggest that even young children are sensitive to the causal structure of a contingency learning task and that the occurrence of blocking in such a task defies an explanation in terms of associative learning theory.

Download Full-text