
Daniela Pamplona
ENSTA-IPParis
incremental learning
fisher information
probabilistic method
1
presentations
SHORT BIO
Daniela Pamplona graduated from Instituto Superior Tecnico, Portugal, in Applied Mathematics and Computation at both Bachelor and Masters levels. She wrote her Masters thesis at the Vislab - Computer and Vision Lab, Institute for Systems and Robotics, under the supervision of Alexandre Bernardino, in space-variant vision for a humanoid robot. From 2009 to 2014, she was a Ph.D. candidate at the Frankfurt Institute for Advanced Studies. Under the supervision of Constantin Rothkopf and Jochen Triesch, she modeled the variability of Retinal Ganglion Cells directly from the statistics of naturalistic images across the field of view. From 2014 to 2016, she was a postdoc at the Biovision team, INRIA Sophia Antipolis. She worked together with Pierre Kornprobst and Bruno Cessac on methods for analyzing neuronal spiking data. Since 2017, she is a postdoc at U2IS, ENSTA- IPParis, with Antoine Manzanera. She develops methods for lifelong learning of visual representations, particularly in the problems of incremental learning and curiosity.
Presentations

Naturally Constrained Online Expectation Maximization
Daniela Pamplona