Search

The limits of molecular dynamics (MD) simulations of macromolecules are steadily pushed forward by the relentless developments of computer architectures and algorithms. This explosion in the number and extent (in size and time) of MD trajectories induces the need of automated and transferable methods to rationalise the raw data and make quantitative sense out of them. Recently, an algorithmic approach was developed by some of us to identify the subset of a protein's atoms, or mapping, that enables the most informative description of it. This method relies on the computation, for a given reduced representation, of the associated mapping entropy, that is, a measure of the information loss due to the simplification. Albeit relatively straightforward, this calculation can be time consuming. Here, we describe the implementation of a deep learning approach aimed at accelerating the calculation of the mapping entropy. The method relies on deep graph networks, which provide extreme flexibility in the input format. We show that deep graph networks are accurate and remarkably efficient, with a speedup factor as large as $10^5$ with respect to the algorithmic computation of the mapping entropy. Applications of this method, which entails a great potential in the study of biomolecules when used to reconstruct its mapping entropy landscape, reach much farther than this, being the scheme easily transferable to the computation of arbitrary functions of a molecule's structure.

Systems developed in wearable devices with sensors onboard are widely used to collect data of humans and animals activities with the perspective of an on-board automatic classification of data. An interesting application of these systems is to support animals' behaviour monitoring gathered by sensors' data analysis. This is a challenging area and in particular with fixed memories capabilities because the devices should be able to operate autonomously for long periods before being retrieved by human operators, and being able to classify activities onboard can significantly improve their autonomy. In this paper, we focus on the identification of prey handling activity in seals (when the animal start attaching and biting the prey), which is one of the main movement that identifies a successful foraging activity. Data taken into consideration are streams of 3D accelerometers and depth sensors values collected by devices attached directly on seals. To analyse these data, we propose an automatic model based on Machine Learning (ML) algorithms. In particular, we compare the performance (in terms of accuracy and F1score) of three ML algorithms: Input Delay Neural Networks, Support Vector Machines, and Echo State Networks. We attend to the final aim of developing an automatic classifier on-board. For this purpose, in this paper, the comparison is performed concerning the performance obtained by each ML approach developed and its memory footprint. In the end, we highlight the advantage of using an ML algorithm, in terms of feasibility in wild animals' monitoring.

EVALITA is a periodic evaluation campaign of Natural Language Processing (NLP) and speech tools for the Italian language. The general objective of EVALITA is to promote the development of language and speech technologies for the Italian language, providing a shared framework where different systems and approaches can be evaluated in a consistent manner. The diffusion of shared tasks and shared evaluation practices is a crucial step towards the development of resources and tools for NLP and speech sciences. The good response obtained by EVALITA, both in the number of participants and in the quality of results, showed that it is worth pursuing such goals for the Italian language. As a side effect of the evaluation campaign, both training and test data are available to the scientific community as benchmarks for future improvements. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC) and it is endorsed by the Italian Association for Artificial Intelligence (AI*IA) and the Italian Association for Speech Sciences (AISV).

Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Recent years have seen heightened attention in this demanding field of research and several new approaches have emerged, such as metric learning on structured data, graph convolutional neural networks, and recurrent decoder networks for structured data. In this contribution, we provide an high-level overview of the state-of-the-art in representation learning and embeddings for structured data across a wide range of machine learning fields., Oral presentation at the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2019) in Bruges, Belgium, on April 24th, 2019

Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes., Comment: Paper at the International Conference of Machine Learning (2018), 2018-07-10 to 2018-07-15 in Stockholm, Sweden

publishedVersion

The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced Deep Echo State Network (DeepESN) model opened the way to an extremely efficient approach for designing deep neural networks for temporal data. At the same time, the study of DeepESNs allowed to shed light on the intrinsic properties of state dynamics developed by hierarchical compositions of recurrent layers, i.e. on the bias of depth in RNNs architectural design. In this paper, we summarize the advancements in the development, analysis and applications of DeepESNs.

Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal representation in deep RNNs through frequency analysis applied to the state signals. The potentiality of our approach is assessed on the class of Multiple Superimposed Oscillator tasks. Furthermore, our investigation provides useful insights to open a discussion on the main aspects that characterize the deep learning framework in the temporal domain., This is a pre-print of the paper submitted to the 27th Italian Workshop on Neural Networks, WIRN 2017

The Internet of Things (IoT) concept is evolving rapidly and influencing newdevelopments in various application domains, such as the Internet of MobileThings (IoMT), Autonomous Internet of Things (A-IoT), Autonomous Systemof Things (ASoT), Internet of Autonomous Things (IoAT), Internetof Things Clouds (IoT-C) and the Internet of Robotic Things (IoRT) etc.that are progressing/advancing by using IoT technology. The IoT influencerepresents new development and deployment challenges in different areassuch as seamless platform integration, context based cognitive network integration,new mobile sensor/actuator network paradigms, things identification(addressing, naming in IoT) and dynamic things discoverability and manyothers. The IoRT represents new convergence challenges and their need to be addressed, in one side the programmability and the communication ofmultiple heterogeneous mobile/autonomous/robotic things for cooperating,their coordination, configuration, exchange of information, security, safetyand protection. Developments in IoT heterogeneous parallel processing/communication and dynamic systems based on parallelism and concurrencyrequire new ideas for integrating the intelligent “devices”, collaborativerobots (COBOTS), into IoT applications. Dynamic maintainability, selfhealing,self-repair of resources, changing resource state, (re-) configurationand context based IoT systems for service implementation and integrationwith IoT network service composition are of paramount importance whennew “cognitive devices” are becoming active participants in IoT applications.This chapter aims to be an overview of the IoRT concept, technologies,architectures and applications and to provide a comprehensive coverage offuture challenges, developments and applications.