Sciweavers

62 search results - page 4 / 13
» Learning Isometric Separation Maps
Sort
View
ALT
2004
Springer
15 years 10 months ago
On Kernels, Margins, and Low-Dimensional Mappings
Kernel functions are typically viewed as providing an implicit mapping of points into a high-dimensional space, with the ability to gain much of the power of that space without inc...
Maria-Florina Balcan, Avrim Blum, Santosh Vempala
117
Voted
ISMIR
2003
Springer
196views Music» more  ISMIR 2003»
15 years 7 months ago
Automatic segmentation, learning and retrieval of melodies using a self-organizing neural network
We introduce a neural network, known as SONNETMAP, capable of automatic segmentation, learning and retrieval of melodies. SONNET-MAP is a synthesis of the SONNET (Self-Organizing ...
S. Harford
107
Voted
ICML
2008
IEEE
16 years 2 months ago
Accurate max-margin training for structured output spaces
Tsochantaridis et al. (2005) proposed two formulations for maximum margin training of structured spaces: margin scaling and slack scaling. While margin scaling has been extensivel...
Sunita Sarawagi, Rahul Gupta
ML
2008
ACM
134views Machine Learning» more  ML 2008»
15 years 1 months ago
Multilabel classification via calibrated label ranking
Label ranking studies the problem of learning a mapping from instances to rankings over a predefined set of labels. Hitherto existing approaches to label ranking implicitly operat...
Johannes Fürnkranz, Eyke Hüllermeier, En...
JMLR
2012
13 years 4 months ago
Deep Learning Made Easier by Linear Transformations in Perceptrons
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Tapani Raiko, Harri Valpola, Yann LeCun