The following special sessions are going to be part of the main programme of ICANN 2017. During the submission phase, you will be able to select whether you would like your\u00a0contribution to considered for\u00a0one of them.<\/p>\n
<\/a><\/p>\n Organisers:\u00a0Lydia Fischer (Honda Research Institute Europe and\u00a0Bielefeld University, Germany),\u00a0Cesare Alippi (Politecnico di Milano, Italy and USI, Switzerland),\u00a0Barbara Hammer (Bielefeld University, Germany).<\/p>\n More information:\u00a0https:\/\/www.techfak.uni-bielefeld.de\/~bhammer\/selfassessment.html<\/a><\/p>\n Self-assessment refers to the ability of a machine learning model to judge the security of its classification. It constitutes a crucial requirement in safety critical applications or whenever a human observer has to validate the given classification such as driver assistance systems, predictive maintenance of plants, or medical classifications; further, self-assessment constitutes one crucial property for classifier fusion. Probabilistic models can naturally be enhanced by the notion of model confidence, and popular deterministic models such as the support vector machine, can be accompanied by an efficient estimate of its confidence. However, while these technologies perform reliably for classical batch classification, their applicability is limited for complex machine learning scenarios such as online learning models, learning scenarios which are subject to drift,\u00a0 heterogeneous models, models which involve complex structured data, or interactive models which incorporate human expertise. The special session aims for contributions connected to the following non-exhaustive list of topics:<\/p>\n <\/a><\/p>\n Organisers: Nowadays a wide range of real-world scenarios yield data streams, i.e. collections of data being generated continuously either over time or over space. E-commerce and banking transactions, weather forecasting recordings and sensor data, customer reports and network traffic records are common examples of data streams produced every day. The special session is intended to collect novel ideas and share different experiences in the field of learning from data streams. Submission of papers covering topics in theoretical and applied learning techniques for data streams are encouraged. Possible topics include (but are not limited to):<\/p>\n <\/a><\/p>\n Organisers: Nowadays, human being\u2019s main worries are about the earth\u2019s health. Although the technological development brought, undoubtedly, countless benefits to our life, likewise it has been accompanied by several troubles for earth planet, which are now threatening its future and our life. Ordinarily, natural and environmental scientists have to cope with complex decision making processes for assessing the potential impacts or risks associated to a given specific threaten at hand, in order to study and implement the necessary initiative to deal with and resolve the problem. However, very often scientists base their work on statistical tools or simple mathematical models incapable to capture the inherent complexities and the interactions of several independent variables. Here is where Neural Networks and more in general, machine learning, come into play. Machine learning techniques, for their nature, possess potentially apt characteristics to address this domain. Therefore, the aim of the workshop is to outline the state-of-the-art of using neural networks, machine learning and the more general field of computational intelligence to real-world environmental and natural science domains, at the same time stimulating the discussion presenting new or little explored case studies to encourage more and more interdisciplinary collaborations in a so fascinating and fundamental application domain.<\/p>\n\n The following special sessions are going to be part of the main programme of ICANN 2017. During the submission phase, you will be able to select whether you would like your\u00a0contribution to considered for\u00a0one of them. S01:\u00a0Self-assessment in advanced machine … Continue reading S01:\u00a0Self-assessment in advanced machine learning models<\/h2>\n
\n
\nS02: Learning from data streams<\/h2>\n
\nGiovanna Castellano (Dept. Computer Science, University of Bari, Italy)
\ngiovanna.castellano\\AT\/uniba.it
\nFrancesco Masulli (Dept. Computer and Information Sciences, University of Genova, Italy) francesco.masulli\\AT\/unige.it<\/p>\n
\nAccordingly there is an urgent need of methods capable to handle and analyze streams of data that are usually vast in volume (or possibly infinite), high-dimensional and changing dynamically. Analysis of data streams requires learning algorithms that are specifically designed not only to handle very large data sets but also to adapt continuously and automatically to smooth evolutions (drifts) and abrupt changes (shifts) in the data distribution.
\nThe main objective of this special session is to discuss the potential of learning techniques in challenging scenarios involving prediction and classification tasks in the realm of data streams.<\/p>\n\n
\nS03:\u00a0Neural Networks meet Natural and Environmental Sciences<\/h2>\n
\nAntonino Staiano, Dipartimento di Scienze e Tecnologie – Universit\u00e0 di Napoli Parthenope (antonino.staiano@uniparthenope.it);
\nGiovanni Burgio, Dipartimento di Scienze Agrarie – Universit\u00e0 di Bologna (giovanni.burgio@unibo.it);
\nGiosu\u00e8 Lo Bosco, Dipartimento di Matematica e Informatica – Universit\u00e0 di Palermo, Italy (giosue.lobosco@unipa.it)<\/p>\n