Find below EMERGE’s news articles, press releases, digests of scientific publications, as well as other outreach materials.
Publication: Residual Reservoir Computing Neural Networks for Time-series Classification
06 October 2023
In this work, EMERGE partners from the University of Pisa introduce a novel class of Reservoir Computing (RC) models, a family of efficiently trainable Recurrent Neural Networks based on untrained connections.
Publication: A Protocol for Continual Explanation of SHAP
06 October 2023
In this paper, EMERGE partners from the University of Pisa tackle XAI for Continual Learning by quantitatively and qualitatively assessing the behavior of one of the most used XAI techniques called SHAP (SHapley Additive exPlanations).
First open meeting of the portfolio of projects funded by the EIC Pathfinder Challenge “Awareness Inside“
27 September 2023
The meeting is taking place Oct. 1st, 2023, in Kraków, Poland, during the 26th European Conference on Artificial Intelligence (ECAI 2023).
Publication: Frappe: fast fiducial detection on low-cost hardware
27 September 2023
In this work, EMERGE partners from the University of Bristol introduce an image processing algorithm called Frappe (Fiducial Recognition Accelerated with Parallel Processing Elements) for detecting and decoding the popular ArUco tags.
Publication: Diversifying Non-dissipative Reservoir Computing Dynamics
22 September 2023
In this work, EMERGE partners from the University of Pisa propose alternative formulations of the reservoirs for EuSNs, aiming at improving the diversity of the resulting dynamics.
Publication: Over-Parameterized Neural Models based on Graph Random Features for fast and accurate graph classification
22 September 2023
In this work, EMERGE partners from the University of Pisa and collaborators explore a simple form of a randomized graph neural network.
Publication: An Untrained Neural Model for Fast and Accurate Graph Classification
22 September 2023
In this work, EMERGE partners from the University of Pisa explore a simple form of a randomized graph neural network inspired by the success of randomized convolutions in the 1-dimensional domain.
Workshop “Inside the Ethics of AI Awareness”
12 September 2023
The workshop presents an opportunity for philosophers, computer scientists, roboticists and other experts to contribute to a nuanced understanding of ethical concerns surrounding artificial systems.
Publication: Model-Based Control for Soft Robots With System Uncertainties and Input Saturation
24 August 2023
In this work, EMERGE partners from Delft University of Technology and collaborators propose a robust model-based strategy for the shape control of soft robots with system uncertainty and input saturation.
