AMALEA: 5th Workshop on Advances in MAchine LEArning
There are many real-world problems of such high complexity that traditional scientific approaches, based on physical and statistical modeling of the data generation mechanism, do not succeed in addressing them efficiently. The cause of inefficiencies often lies in multidimensionality, nonlinearities, chaotic phenomena and the presence of a plethora of degrees of freedom and unknown parameters in the mechanism that generates data. As a result, loss of information that is crucial to solve a problem is inherent in the data generation process itself, making a traditional mathematical solution intractable.
At the same time, however, biological systems have evolved to address similar problems in efficient ways. In nature, we observe abundant examples of high level intelligence arising via inter-networking components of only elementary intelligence:
Biological neural networks, i.e., networks of interconnected biological neurons in the nervous system of most multi-cellular animals, are capable of learning, memorizing and recognizing patterns in signals such as images, sounds, smells or odors.
Ants exhibit a collective, decentralized, and self-organized intelligence that allows them to discover the shortest route to food in very efficient ways.
Similar ideas are true with regards to immune systems, social networks, financial and business networks, or graphs.
Background and Goals
There are many real-world problems of such high complexity that traditional scientific approaches, based on physical and statistical modeling of the data generation mechanism, do not succeed in addressing them efficiently. The cause of inefficiencies often lies in multidimensionality, nonlinearities, chaotic phenomena and the presence of a plethora of degrees of freedom and unknown parameters in the mechanism that generates data. As a result, loss of information that is crucial to solve a problem is inherent in the data generation process itself, making a traditional mathematical solution intractable.
At the same time, however, biological systems have evolved to address similar problems in efficient ways. In nature, we observe abundant examples of high level intelligence arising via inter-networking components of only elementary intelligence:
Biological neural networks, i.e., networks of interconnected biological neurons in the nervous system of most multi-cellular animals, are capable of learning, memorizing and recognizing patterns in signals such as images, sounds, smells or odors.
Ants exhibit a collective, decentralized, and self-organized intelligence that allows them to discover the shortest route to food in very efficient ways.
Similar ideas are true with regards to immune systems, social networks, financial and business networks, or graphs
Topics of Interests
Topics of interest for this special session include, but not limited to:
biological and artificial neural networks
biological and artificial immune networks
biological and artificial swarm intelligence
genetic/evolutionary computing
fuzzy and neuro-fuzzy systems
belief networks
ensemble classifiers
deep belief networks/ deep learning approaches
advances in statistical learning
Petri nets
graph methods
ontologies
Bayesian/statistical methods
optimization methods in knowledge engineering
Applications
Call for Papers
Important Dates
Chairs
Session Chairs:
Professor-Dr. George A. Tsihrintzis, University of Piraeus
Dr. Aristomenis Lampropoulos, National Documentation Center (NDC)/ National Hellenic Research Foundation (NHRF)
Dr. Dionysios Sotiropoulos, Athens University of Economics and Business
Program Committee
Program Session Committee:
- Dr. Nikolaos Houssos, National Documentation Center (NDC)/ National Hellenic Research Foundation (NHRF), Greece
- Prof. Łukasz Bolikowski, Centre for Open Science, University of Warsaw
More PC Members TBA
Instructions for Authors
Contact Information:
Prof.-Dr. George A. Tsihrintzis
University of Pireaus
e-mail: geoatsi@unipi.gr