Publication

Multi-Armed Bandits for Addressing the Exploration/Exploitation Trade-off in Self Improving Learning Environment

Related publications (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Leveraging over prior knowledge for online learning of visual categories

Barbara Caputo, Tatiana Tommasi, Mohsen Kaboli

Open ended learning is a dynamic process based on the continuous analysis of new data, guided by past experience. On one side it is helpful to take advantage of prior knowledge when only few information on a new task is available (transfer learning). On th ...

2012

Putting the user into the active learning loop: towards realistic but efficient photointerpretation

Devis Tuia

In recent years, several studies have been published about the smart definition of training set using active learning algorithms. However, none of these works consider the contradiction between the active learning methods, which rank the pixels according t ...

Ieee2012

Iterative Learning of Feed-Forward Corrections for High-Performance Tracking

We revisit a recently developed iterative learning algorithm that enables systems to learn from a repeated operation with the goal of achieving high tracking performance of a given trajectory. The learning scheme is based on a coarse dynamics model of the ...

2012

Open-Ended Learning of Visual and Multi-Modal Patterns

Jie Luo

A common trend in machine learning and pattern classification research is the exploitation of massive amounts of information in order to achieve an increase in performance. In particular, learning from huge collections of data obtained from the web, and us ...

EPFL2011

Open-ended Learning of Visual and Multi-modal Patterns

Jie Luo

Ecole polytechnique fédérale de Lausanne2011

An evaluation of e-learning in Healthcare

Nikolaos Maris

As new technologies enable a radical transformation of the learning process, new learning approaches and techniques appear, and the need for quality assurance of all learning assets emerges. Although, the existing e-learning standards have managed to cover ...

IGI Global2011

Multiclass Transfer Learning from Unconstrained Priors

Barbara Caputo, Jie Luo, Tatiana Tommasi

The vast majority of transfer learning methods proposed in the visual recognition domain over the last years ad- dresses the problem of object category detection, assuming a strong control over the priors from which transfer is done. This is a strict condi ...

2011

Multiclass Transfer Learning from Unconstrained Priors

Barbara Caputo, Jie Luo, Tatiana Tommasi

Idiap2011

Geomatics E-learning with Exomatic: Implementation and Assessment

Pierre-Yves Gilliéron, Arnaud Deshogues

The Geodetic Engineering Laboratory (TOPO) at the Swiss Federal Institute of Technology (EPFL) has introduced e- learning into its undergraduate topography course. The Centre for Research and Support of Training and its Technologies (CRAFT) has introduced ...

IATED2009

An online framework for learning novel concepts over multiple cues

Barbara Caputo, Jie Luo

We propose an online learning algorithm to tackle the problem of learning under limited computational resources in a teacher-student scenario, over multiple visual cues. For each separate cue, we train an online learning algorithm that sacrifices performan ...

2009