#### Filter Results:

- Full text PDF available (7)

#### Publication Year

2003

2019

- This year (3)
- Last 5 years (8)
- Last 10 years (16)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Karim T. Abou-Moustafa, Fernando De la Torre, Frank P. Ferrie
- IEEE Computer Society Conference on Computer…
- 2010

Linear Discriminant Analysis (LDA) is a popular tool for multiclass discriminative dimensionality reduction. However, LDA suffers from two major problems: (1) It only optimizes the Bayes error for… (More)

- Karim T. Abou-Moustafa, Mohamed Cheriet, Ching Y. Suen
- Pattern Recognition Letters
- 2004

This paper investigates the effect of HMM structure on the performance of HMM-based classifiers. The investigation is based on the framework of graphical models, the diffusion of credits of HMMs and… (More)

A generative-discriminative hybrid for sequential data classification [image classification example]

- Karim T. Abou-Moustafa, Ching Y. Suen, Mohamed Cheriet
- IEEE International Conference on Acoustics…
- 2004

Classification of sequential data using discriminative models such as support vector machines is very hard due to the variable length of this type of data. On the other hand, generative models such… (More)

- Karim T. Abou-Moustafa, Frank P. Ferrie
- ACML
- 2012

Multivariate Gaussian densities are pervasive in pattern recognition and machine learning. A central operation that appears in most of these areas is to measure the dierence between two multivariate… (More)

- Karim T. Abou-Moustafa, Frank P. Ferrie
- DAGM-Symposium
- 2007

We propose an unsupervised "local learning" algorithm for learning a metric in the input space. Geometrically, for a given query point, the algorithm finds the minimum volume ellipsoid (MVE) covering… (More)

- Karim T. Abou-Moustafa, Mohak Shah, Fernando De la Torre, Frank P. Ferrie
- DAGM-Symposium
- 2011

Many unsupervised learning algorithms make use of kernels that rely on the Euclidean distance between two samples. However, the Euclidean distance is optimal for Gaussian distributed data. In this… (More)

- Karim T. Abou-Moustafa, Fernando De la Torre, Frank P. Ferrie
- Pattern Recognition
- 2015

We address the class masking problem in multiclass linear discriminant analysis (LDA). In the multiclass setting, LDA does not maximize each pairwise distance between classes, but rather maximizes… (More)

- Karim T. Abou-Moustafa, Csaba Szepesvári
- ArXiv
- 2017

We consider a priori generalization bounds developed in terms of cross-validation estimates and the stability of learners. In particular, we first derive an exponential Efron-Stein type tail… (More)

- Karim T. Abou-Moustafa
- IEEE Pulse
- 2016

Digitally recorded data have become another critical natural resource in our current research environment. This reality is one of the tremendous victories for decades of research in computer… (More)

- Karim T. Abou-Moustafa, Mohamed Cheriet, Ching Y. Suen
- Ninth International Workshop on Frontiers in…
- 2004

Classification of time-series data using discriminative models such as SVMs is very hard due to the variable length of this type of data. On the other hand generative models such as HMMs have become… (More)