#### Filter Results:

- Full text PDF available (55)

#### Publication Year

1981

2018

- This year (2)
- Last 5 years (15)
- Last 10 years (28)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Method

#### Organism

Learn More

- Christos Sotiriou, Soek-Ying Neo, +7 authors Edison T. Liu
- Proceedings of the National Academy of Sciences…
- 2003

Comprehensive gene expression patterns generated from cDNA microarrays were correlated with detailed clinico-pathological characteristics and clinical outcome in an unselected group of 99… (More)

- Yi Li, Philip M. Long
- Machine Learning
- 1999

We describe a new incremental algorithm for training linear threshold functions: the Relaxed Online Maximum Margin Algorithm, or ROMMA. ROMMA can be viewed as an approximation to the algorithm that… (More)

- Philip M. Long, Rocco A. Servedio
- Machine Learning
- 2008

A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class includes AdaBoost,… (More)

- Yi Li, Philip M. Long, Aravind Srinivasan
- SODA
- 2000

1 I n t r o d u c t i o n Many important applied problems can be modeled as learning from random examples. Examples include text categorization [22], handwrit ten character recognition [16, 4, 8],… (More)

- Shai Ben-David, Nicolò Cesa-Bianchi, Philip M. Long
- COLT
- 1992

We investigate the PAC learnability of classes of {0,…,n}-valued functions. For n = 1, it is known that the finiteness of the Vapnik-Chervonenkis dimension is necessary and sufficient for learning.… (More)

- Shai Ben-David, Nadav Eiron, Philip M. Long
- COLT
- 2000

We address the computational complexity of learning in the agnostic framework. For a variety of common concept classes we prove that, unless P=NP, there is no polynomial time approximation scheme for… (More)

- Philip M. Long, Lei Tan
- Machine Learning
- 1996

We describe a polynomial-time algorithm for learning axis-aligned rectangles in Q d with respect to product distributions from multiple-instance examples in the PAC model. Here, each example consists… (More)

We consider the problem of learning real-valued functions from random examples when the function values are corrupted with noise. With mild conditions on independent observation noise, we provide… (More)

- Philip M. Long, Manfred K. Warmuth
- COLT
- 1990

- Nicolas Olivier Fortunel, Hasan H. Otu, +13 authors Bing Lim
- Science
- 2003

Ramalho-Santos et al. (1) and Ivanova et al. (2), comparing the same three “stem cells”— embryonic stem cells (ESCs); neural stem cells (NSCs), referred to as neural progenitor/stem cells (NPCs) in… (More)