[:fr]
Hande Alemdar
Post-doctoral Researcher
SLIDE research group
Contact Information
Laboratoire d’Informatique de Grenoble (LIG)
Université Grenoble Alpes (UGA)
Bâtiment IMAG – Bureau 310
700 Avenue Centrale
38401 Saint-Martin d’Hères – FRANCE
Tel: +33 4 57 42 16 10
Email: FirstName.LastName@univ-grenoble-alpes.fr
You can find me on Google Scholar, Web of Science, Research Gate, DBLP
You can follow me on twitter
Research Interests
Machine Learning and Pattern Recognition
Deep Learning, Probabilistic Models, Active Learning, Semi-supervised Learning, Transfer Learning
Data Science
Real World Big Data Mining, Sports Analytics, Privacy Implications of Data Analytics
Pervasive and Ubiquitous Computing
Human activity recognition, Behavior analysis, Ambient Assisted Living (AAL) Applications
Projects
Researching deep learning algorithms on a hardware solution for pattern mining in high throughput data streams. This solution, which could be proposed as a support hardware card, will be able to test simultaneously the presence of a large number of patterns in the data. The benefits of such a solution are (i) to process faster streams than purely software approaches, and (ii) to use less servers to process data streams, thus reducing energy consumption. I study on constrained deep neural networks with binary and ternary weights in order to make use of this power efficient hardware without compromising accuracy.
Nano2017 ESPRIT : Mining data streams with hardware support[:en]
Hande Alemdar
Post-doctoral Researcher
SLIDE research group
Contact Information
Laboratoire d’Informatique de Grenoble (LIG)
Université Grenoble Alpes (UGA)
Bâtiment IMAG – Bureau 310
700 Avenue Centrale
38401 Saint-Martin d’Hères – FRANCE
Tel: +33 4 57 42 16 10
Email: FirstName.LastName@univ-grenoble-alpes.fr
You can find me on Google Scholar, Web of Science, Research Gate, DBLP
You can follow me on twitter
Research Interests
Machine Learning and Pattern Recognition
Deep Learning, Probabilistic Models, Active Learning, Semi-supervised Learning, Transfer Learning
Data Science
Real World Big Data Mining, Sports Analytics, Privacy Implications of Data Analytics
Pervasive and Ubiquitous Computing
Human activity recognition, Behavior analysis, Ambient Assisted Living (AAL) Applications
Projects
Researching deep learning algorithms on a hardware solution for pattern mining in high throughput data streams. This solution, which could be proposed as a support hardware card, will be able to test simultaneously the presence of a large number of patterns in the data. The benefits of such a solution are (i) to process faster streams than purely software approaches, and (ii) to use less servers to process data streams, thus reducing energy consumption. I study on constrained deep neural networks with binary and ternary weights in order to make use of this power efficient hardware without compromising accuracy.
Nano2017 ESPRIT : Mining data streams with hardware support[:]
