2027 search results - page 76 / 406 » Learning and Generalization with the Information Bottleneck |
CONNECTION
2004
14 years 9 months ago
2004
While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. ...
ICONIP
2009
14 years 7 months ago
2009
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
CSCW
2012
ACM
13 years 5 months ago
2012
ACM
Photoshop with Friends is an online community of learners exchanging just-in-time help on graphic design tasks. The system attempts to provide an interactive, visual, context-awar...
SIGCSE
2005
ACM
15 years 3 months ago
2005
ACM
The author shares techniques used in a successful "Ethics and Professionalism" class at California State University, San Bernardino. The author describes active learning...
ICONIP
2009
14 years 7 months ago
2009
It is generally assumed in the traditional formulation of supervised learning that only the outputs data are uncertain. However, this assumption might be too strong for some learni...