posted by user: claudiogalicchio || 1250 views || tracked by 7 users: [display]

Randomized Neural Networks - ESANN 2018 : Randomized Neural Networks - Special Session @ ESANN 2018


When Apr 25, 2018 - Apr 27, 2018
Where Bruges, Belgium
Submission Deadline Nov 20, 2017
Notification Due Jan 31, 2018
Categories    neural networks   reservoir computing   echo state networks   machine learning

Call For Papers

Scope and Topics
The use of randomization in the design of Neural Networks (NNs) has become increasingly popular, mainly due to the ease of implementation, extreme efficiency of the training algorithms and the possibility of analyzing the NNs properties that are independent from learning. Randomization can enter NN design in various disguises, for example in the model construction and training (e.g. random setting of a subset of weights), or in its functionality and regularization algorithms (e.g. inclusion of random noise in activation layers, drop-out techniques, etc.). Under a broader perspective, the analysis of randomized models naturally extends to a general Machine Learning (ML) context (e.g. random projections). Moreover, Learning in Structured Domains and Deep Learning represent ML research areas for which this type of analysis is highly beneficial.

This session calls for contributions targeting novel theoretical and/or empirical studies on randomization in NNs, and it is proposed as an opportunity for discussing the advantages and limitations/shortcomings of the approach under an open and critical perspective.

The topics of interest for the session include, but are not limited, to the following:

-Neural Networks with random weights
-Randomized Machine Learning algorithms
-Reservoir Computing and Echo State Networks
-Extreme Learning Machines and Random Vector Functional-Link Networks
-Random Projections and Neural Networks
-Randomized regularization techniques
-Bias of randomization in the design of Neural Networks
-Theoretical analysis: advantages and shortcomings (range of applicability, stability, -efficiency, etc.)
-Deep Randomized Neural Networks
-Randomized approaches for Learning in Structured Domains (sequences, trees, graphs)
-Efficient implementations of Randomized Neural Networks
-Applications and comparisons

Important Dates
* Paper submission deadline: 20 November 2017

* Notification of acceptance: 31 January 2018

* ESANN conference: Bruges, Belgium, 25-27 April 2018

Paper Submission

Papers submitted to this Special Session are reviewed according to the same rules as the submissions to the regular sessions of ESANN 2018. Authors who submit papers to this session are invited to mention it on the author submission form. Submissions to regular and special sessions follow identical format, instructions, deadlines and procedures.

Please find more info at the ESANN 2018 website

Special Session Organizers
Claudio Gallicchio (University of Pisa, Italy),
Alessio Micheli (University of Pisa, Italy)
Peter Tino (University of Birmingham, United Kingdom)

Related Resources

ICPR 2018   24th International Conference on Pattern Recognition
ESANN 2018   European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
ICAISC 2018   International Conference on Artificial Intelligence and Soft Computing
PAKDD 2018   The 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining
WCCI 2018   World Congress on Computational Intelligence
ECCV 2018   European Conference on Computer Vision
CVPR 2018   Computer Vision and Pattern Recognition
ISNN 2018   15th International Symposium on Neural Networks
ICONIP 2017   International Conference on Neural Information Processing
ASYNC 2018   24st IEEE International Symposium on Asynchronous Circuits and Systems