Managing plant diseases is increasingly difficult due to reasons such as intensifying the field production, climatic change-driven expansion of pests, redraw and loss of effectiveness of pesticides, rapid breakdown of the disease resistance in the field, and other factors. The substantial progress in genomics of both plants and pathogens, achieved in the last decades, has the potential to counteract this negative trend, however, only when the genomic data is supported by relevant phenotypic data that allows linking the genomic information to specific traits. We have developed a set of methods and equipment and combined them into a “Macrophenomics facility.” The pipeline has been optimized for the quantification of powdery mildew infection symptoms on wheat and barley, but it can be adapted to other diseases and host plants. The Macrophenomics pipeline scores the visible powdery mildew disease symptoms, typically 5-7 days after inoculation (dai), in a highly automated manner. The system can precisely and reproducibly quantify the percentage of the infected leaf area with a theoretical throughput of up to 10000 individual samples per day, making it appropriate for phenotyping of large germplasm collections and crossing populations.

Held yearly, the objective of BNAIC is to promote and disseminate recent research developments in Artificial Intelligence within Belgium, Luxembourg and the Netherlands. However, it does not exclude contributions from countries outside the Benelux. As in previous years, BNAIC 2016 welcomed four types of contributions, namely A) regular papers, B) compressed contributions, C) demonstration abstracts, and D) thesis abstracts.We received 93 submissions, consisting of 24 regular papers, 47 short papers, 11 demonstration abstracts and 11 thesis abstracts. After a thorough review phase by the Program Committee, the conference chairs made the final acceptance decisions. The overall acceptance rate was 88% (63% for regular papers, 100% for compressed contributions and demonstration abstracts, and 91% for thesis abstracts).In addition to the regular research presentations, posters and demonstrations, we were happy to include several other elements in the program of BNAIC 2016, among To conclude, we want to express our gratitude to all people who made this conference possible: in addition to all invited speakers mentioned above, many thanks to all organizing and program committee members for their hard work in assuring the high quality of this conference. Moreover, we wish to thank all student volunteers, administrative and secretarial assistants, and of course our sponsors. We also gratefully acknowledge help from the BNVKI and from previous organizers. And last, but certainly not least, we cordially thank all the authors who made important contributions to the conference. Without their efforts, this conference could not have taken place. Inference that aims at determining whether a hypothesis is entailed by a text. Usually tackled by machine learning techniques employing features which represent similarity between texts, the recent availability of more training data presupposes that Neural Networks that are able to learn latent feature from data for generalized prediction could be employed. This paper employs the Child-Sum Tree-LSTM for solving the challenging problem of textual entailment. Our approach is simple and able to generalize well without excessive parameter optimization. Evaluation done on SNLI, SICK and other TE datasets shows the competitiveness of our approach.

We discuss the use of matrix relevance learning, a popular extension to prototype learning algorithms, applied to a three-class classification task of diagnosing cassava diseases from spectral data. Previously this diagnosis has been done using plant image data taken with a smartphone. However for this method disease symptoms need to be visible. Unfortunately for some cassava diseases, once symptoms have manifested on the aerial part of the plant, the root which is the edible part of the plant has been totally destroyed. This research is premised on the hypothesis that diseased crops without visible symptoms can be detected using spectral information, allowing for early interventions. In this paper, we analyze visible and near-infrared spectra captured from leaves infected with two common cassava diseases (cassava brown streak disease and cassava mosaic virus disease) found in Sub-Saharan Africa. We also take spectra from leaves of healthy plants. The spectral data come with thousands of dimensions, therefore different wavelengths are analyzed in order to identify the most relevant spectral bands for diagnosing these disease. To cope with the nominally high number of input dimensions of data, functional decomposition of the spectra is applied. The classification task is addressed using Generalized Matrix Relevance Learning Vector Quantization and compared with the standard classification techniques performed in the space of expansion coefficients.INDEX TERMS Cassava disease diagnosis, feature selection, matrix relevance learning, spectral data.

In this contribution, we consider the classification of time series and similar functional data which can be represented in complex Fourier and wavelet coefficient space. We apply versions of learning vector quantization (LVQ) which are suitable for complex-valued data, based on the so-called Wirtinger calculus. It allows for the formulation of gradient-based update rules in the framework of cost-function-based generalized matrix relevance LVQ (GMLVQ). Alternatively, we consider the concatenation of real and imaginary parts of Fourier coefficients in a real-valued feature vector and the classification of time-domain representations by means of conventional GMLVQ. In addition, we consider the application of the method in combination with wavelet-space features to heartbeat classification.