State-space models constitute an effective modeling tool to describe multivariate time series and operate by maintaining an updated representation of the system state from which predictions are made.
Predicting structural and energetic properties of a molecular system is one of the fundamental tasks in molecular simulations, and it has use cases in chemistry, biology, and medicine.
Hypergraph representations are both more efficient and better suited to describe data characterized by relations between two or more objects.
In recent years, the machine learning community has seen a continuous growing interest in research aimed at investigating dynamical aspects of both training procedures and machine learning models.
Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance.
In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations.
Ranked #1 on Graph Classification on Bench-hard
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks.
Finding such a region requires searching in hyper-parameter space in a sensible way: hyper-parameter configurations marginally outside such a region might yield networks exhibiting fully developed chaos, hence producing unreliable computations.
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function.
Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters.
Ranked #4 on Skeleton Based Action Recognition on SBU
Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for some relevant properties of data, like hierarchy and circularity.
Echo State Networks (ESNs) are simplified recurrent neural network models composed of a reservoir and a linear, trainable readout layer.
Simulations conducted on a controlled benchmark task confirm the relevance of these attractors for interpreting the behaviour of recurrent neural networks, at least for tasks that involve learning a finite number of stable states and transitions between them.
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network.
Given a finite sequence of graphs, e. g., coming from technological, biological, and social networks, the paper proposes a methodology to identify possible changes in stationarity in the stochastic process generating the graphs.
A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs.
In this work, we propose a novel autoencoder architecture based on recurrent neural networks to generate compressed representations of MTS.
The proposed methodology consists in embedding graphs into a geometric space and perform change detection there by means of conventional methods for numerical streams.
We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF).
In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space.
We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure.
In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in recurrent neural networks.
We verify that the determination of the edge of stability provided by such RQA measures is more accurate than two well-known criteria based on the Jacobian matrix of the reservoir.
We assume that such a dynamical process is predictable to a certain degree by means of a class of recurrent networks called Echo State Network (ESN), which are capable to model a generic dynamical process.
The subjects belong to two different groups, formed by four and eight subjects with, respectively, high- and low-amplitude rest tremors.
In this paper, we face the problem of joint optimization of both topology and network parameters in a real smart grid.
This paper presents the SPARE C++ library, an open source software tool conceived to build pattern recognition and soft computing systems.
We propose a multi-agent algorithm able to automatically discover relevant regularities in a given dataset, determining at the same time the set of configurations of the adopted parametric dissimilarity measure yielding compact and separated clusters.
Representing patterns as labeled graphs is becoming increasingly common in the broad field of computational intelligence.
We evaluate a version of the recently-proposed classification system named Optimized Dissimilarity Space Embedding (ODSE) that operates in the input space of sequences of generic objects.
This paper deals with the relations among structural, topological, and chemical properties of the E. Coli proteome from the vantage point of the solubility/aggregation propensity of proteins.
This paper builds upon the fundamental work of Niwa et al. , which provides the unique possibility to analyze the relative aggregation/folding propensity of the elements of the entire Escherichia coli (E. coli) proteome in a cell-free standardized microenvironment.
The proposed framework is conceived (i) to offer a guideline for the synthesis of information granules and (ii) to build a groundwork to compare and quantitatively judge over different data granulation procedures.
Modern electric power grids (smart grids) are equipped with smart sensors that allow to gather real-time information regarding the physical status of all the component elements belonging to the whole infrastructure (e. g., cables and related insulation, transformers, breakers and so on).