2455 search results - page 337 / 491 » Learning Composite Concepts |
161
click to vote
AI
1998
Springer
15 years 6 months ago
1998
Springer
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
164
click to vote
SIGIR
2002
ACM
15 years 6 months ago
2002
ACM
We describe a new family of topic-ranking algorithms for multi-labeled documents. The motivation for the algorithms stems from recent advances in online learning algorithms. The a...
172
click to vote
SP
2002
IEEE
15 years 6 months ago
2002
IEEE
Markov models have been used extensively in psychology of learning. Applications of hidden Markov models are rare however. This is partially due to the fact that comprehensive stat...
180
click to vote
SOCROB
2010
2010
Using the Interaction Rhythm as a Natural Reinforcement Signal for Social Robots: A Matter of Belief
15 years 4 months ago
Abstract. In this paper, we present the results of a pilot study of a human robot interaction experiment where the rhythm of the interaction is used as a reinforcement signal to le...
183
click to vote
ICCV
2005
IEEE
16 years 1 days ago
2005
IEEE
When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a per...