Meta-learning, or "learning to learn", refers techniques that infer an inductive bias from data corresponding multiple related tasks with the goal of improving sample efficiency for new, previously unobserved, tasks. A key performance measure meta-learning is meta-generalization gap, is, difference between average loss measured on meta-training and a randomly selected task. This paper presents ...

This study used peripheral precueing to explore the effect of covert transient attention on performance in spatial resolution tasks. Experiments 1 (Landolt-square) and 2 (‘broken-line’) measured gap resolution and Experiment 3 measured vernier resolution. In all three tasks the target was presented alone in a large number of possible locations, ranging from 1.5–6° of eccentricity in the vertica...

Whereas today‟s information systems are well-equipped for efficient query handling, their strict mathematical foundations hamper their use for everyday tasks. In daily life, people expect information to be offered in a personalized and focused way. But currently, personalization in digital systems still only takes explicit knowledge into account and does not yet process conceptual information o...

Robust low-level image features have proven to be effective representations for a variety of high-level visual recognition tasks, such as object recognition and scene classification. But as the visual recognition tasks become more challenging, the semantic gap between low-level feature representation and the meaning of the scenes increases. In this paper, we propose to use objects as attributes...

The main impediment to a widespread use of geographic information using a geographic information system (GIS) is the gap between the user’s expression of a task within the context of an activity and the sequence of operations within a GIS needed to successfully perform that task. Users express their intentions and supporting activities in a high level language, usually in natural language. This...