Sciweavers

2440 search results - page 39 / 488
» Learn .MT: A New Approach to Incremental Learning
Sort
View
ML
2007
ACM
131views Machine Learning» more  ML 2007»
14 years 11 months ago
A primal-dual perspective of online learning algorithms
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer
93
Voted
NAACL
2007
15 years 1 months ago
Source-Language Features and Maximum Correlation Training for Machine Translation Evaluation
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Ding Liu, Daniel Gildea
KAIS
2000
106views more  KAIS 2000»
14 years 11 months ago
FANNC: A Fast Adaptive Neural Network Classifier
In this paper, a fast adaptive neural network classifier named FANNC is proposed. FANNC exploits the advantages of both adaptive resonance theory and field theory. It needs only on...
Zhi-Hua Zhou, Shifu Chen, Zhaoqian Chen
AH
2008
Springer
15 years 6 months ago
Learner Modelling in Exploratory Learning for Mathematical Generalisation
Exploratory learning supports creative thinking, allowing learners to control their own learning process, whilst it provides them with help and guidance when necessary. This pedago...
Mihaela Cocea
NEUROSCIENCE
2001
Springer
15 years 4 months ago
Analysis and Synthesis of Agents That Learn from Distributed Dynamic Data Sources
We propose a theoretical framework for specification and analysis of a class of learning problems that arise in open-ended environments that contain multiple, distributed, dynamic...
Doina Caragea, Adrian Silvescu, Vasant Honavar