Claudio Gallicchio
YOU?
Author Swipe
View article: Embedded deep reservoir computing for modelling complex industrial systems
Embedded deep reservoir computing for modelling complex industrial systems Open
Industrial processes are becoming increasingly complex, requiring advanced modelling techniques to understand their behaviour and improve their performance. In this context, deep learning algorithms have proven to be effective tools for mo…
View article: Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks Open
Echo State Networks (ESNs) are a particular type of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) framework, popular for their fast and efficient learning. However, traditional ESNs often struggle with long…
View article: Mixture of Raytraced Experts
Mixture of Raytraced Experts Open
We introduce a Mixture of Raytraced Experts, a stacked Mixture of Experts (MoE) architecture which can dynamically select sequences of experts, producing computational graphs of variable width and depth. Existing MoE architectures generall…
View article: Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling Open
The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate by applying SSM modules to sequences ex…
View article: On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems Open
A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in information transmission as…
View article: Machine learning for prediction of sea ice stability
Machine learning for prediction of sea ice stability Open
Arctic sea ice, the vast body of frozen water near the North Pole, has been in steady decline since satellite observations began. While state-of-the-art models attempt to project future scenarios, they often show significant discrepancies,…
View article: A memristive computational neural network model for time-series processing
A memristive computational neural network model for time-series processing Open
In this work, we introduce a novel computational framework inspired by the physics of memristive devices and systems, which we embed into the context of Recurrent Neural Networks (RNNs) for time-series processing. Our proposed memristive-f…
View article: Ray-Tracing for Conditionally Activated Neural Networks
Ray-Tracing for Conditionally Activated Neural Networks Open
In this paper, we introduce a novel architecture for conditionally activated neural networks combining a hierarchical construction of multiple Mixture of Experts (MoEs) layers with a sampling mechanism that progressively converges to an op…
View article: On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning Open
Graph Neural Networks (GNNs) are models that leverage the graph structure to transmit information between nodes, typically through the message-passing operation. While widely successful, this approach is well known to suffer from the over-…
View article: GRAMA: Adaptive Graph Autoregressive Moving Average Models
GRAMA: Adaptive Graph Autoregressive Moving Average Models Open
Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural Networks (GNNs) in modeling long-range interactions. Despite their success, existing methods either compromise on permutation equivariance or limit their…
View article: Sparse Reservoir Topologies for Physical Implementations of Random Oscillators Networks
Sparse Reservoir Topologies for Physical Implementations of Random Oscillators Networks Open
Physical implementation of recurrent neural networks is hindered by the fact that hidden units need to be trained and are often fully-connected. We propose to relieve both these constraints by adopting and improving on an oscillators-based…
View article: Tutorial on Sustainable Deep Learning for Time-series: Reservoir Computing
Tutorial on Sustainable Deep Learning for Time-series: Reservoir Computing Open
International audience
View article: Investigating over-parameterized randomized graph networks
Investigating over-parameterized randomized graph networks Open
In this paper, we investigate neural models based on graph random features for classification tasks. First, we aim to understand when over parameterization, namely generating more features than the ones necessary to interpolate, may be ben…
View article: Decentralized Incremental Federated Learning with Echo State Networks
Decentralized Incremental Federated Learning with Echo State Networks Open
Federated Echo State Networks proved their efficiency in learning low-resource collaborative settings where data is regulated privacy. In this work, we broaden the applicability of this machine learning approach to a decentralized setting,…
View article: Long Range Propagation on Continuous-Time Dynamic Graphs
Long Range Propagation on Continuous-Time Dynamic Graphs Open
Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurre…
View article: TEACHING Platform for Human-Centric Autonomous Applications: Design and Overview
TEACHING Platform for Human-Centric Autonomous Applications: Design and Overview Open
The TEACHING project enhances AI applications in pervasive environments via Humanistic Intelligence, fostering synergy between humans and Cyber-Physical Systems of Systems (CPSoS). Here, we present the TEACHING Platform, a microservice-bas…
View article: Residual Echo State Networks: Residual recurrent neural networks with stable dynamics and fast learning
Residual Echo State Networks: Residual recurrent neural networks with stable dynamics and fast learning Open
Residual connections have been established as a staple for modern deep learning architectures. Most of their applications are cast towards feedforward computing. In this paper, we study the architectural bias of residual connections in the…
View article: Edge of Stability Echo State Network
Edge of Stability Echo State Network Open
Echo state networks (ESNs) are time series processing models working under the echo state property (ESP) principle. The ESP is a notion of stability that imposes an asymptotic fading of the memory of the input. On the other hand, the resul…
View article: Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks Open
The dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning, especially when considering long-range propagation. This calls for principled approaches that control and r…
View article: On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems Open
A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in information transmission as…
View article: Euler State Networks: Non-dissipative Reservoir Computing
Euler State Networks: Non-dissipative Reservoir Computing Open
Inspired by the numerical solution of ordinary differential equations, in this paper, we propose a novel Reservoir Computing (RC) model, called the Euler State Network (EuSN). The presented approach makes use of forward Euler discretizatio…
View article: Awareness in robotics: An early perspective from the viewpoint of the EIC Pathfinder Challenge "Awareness Inside''
Awareness in robotics: An early perspective from the viewpoint of the EIC Pathfinder Challenge "Awareness Inside'' Open
Consciousness has been historically a heavily debated topic in engineering, science, and philosophy. On the contrary, awareness had less success in raising the interest of scholars in the past. However, things are changing as more and more…
View article: Enhancing Echo State Networks with Gradient-based Explainability Methods
Enhancing Echo State Networks with Gradient-based Explainability Methods Open
Recurrent Neural Networks are effective for analyzing temporal data, such as time series, but they often require costly and time-intensive training. Echo State Networks simplify the training process by using a fixed recurrent layer, the re…
View article: Improving Fairness via Intrinsic Plasticity in Echo State Networks
Improving Fairness via Intrinsic Plasticity in Echo State Networks Open
Artificial Intelligence, and in particular Machine Learning, has become ubiquitous in today's society, both revolutionizing and impacting society as a whole. However, it can also lead to algorithmic bias and unfair results, especially when…
View article: Communication-Efficient Ridge Regression in Federated Echo State Networks
Communication-Efficient Ridge Regression in Federated Echo State Networks Open
Federated Echo State Networks represent an efficient methodology for learning in pervasive environments with private temporal data due to the low computational cost required by the learning phase. In this paper, we propose Partial Federate…