Workshop: AI in Drug Discovery
The Workshop on AI in Drug Discovery invites cutting-edge contributions in the rapidly evolving field of AI-driven drug discovery. We are seeking submissions encompassing various facets such as generative models, explainable AI, model distillation, uncertainty quantification, reaction informatics and synthetic route prediction, quantum machine learning
for reactivity, methodologies for mining very large compound data sets, federated learning, analysis of HTS data and identification of frequent hitters and other topics related to the use of ML in chemistry.
ORGANIZERS: Igor Tetko (Institute of Structural Biology, Helmholtz Zentrum Munich Neuherberg, Germany), Djork-Arné Clevert (Pfizer, Berlin, Germany)
TOPICS:
Big Data and advanced machine learning in chemistry
eXplainable AI (XAI) in chemistry
Chemoinformatics
Use of deep learning to predict molecular properties
Modeling and prediction of chemical reaction data
Generative models
See details in AI Drug Discovery Call for Papers.
Workshop: Explainable AI in Human-Robot Interaction
The workshop will be held for the dissemination and discussion of results from
the MSCA EU-project TRAIL (Transparent, Interpretable Robots). The topic
of the project is Explainability and Transparency in artificial neural networks
(decision transparency) and in human-robot interactions (behavior
transparency).
ORGANIZERS: Stefan Wermter (University of Hamburg, Germany), Angelo Cangelosi (University of Manchester, UK), Igor Farkaš (Comenius University of Bratislava, Slovakia), Theresa Pekarek Rosin (University of Hamburg, Germany)
See details in XAI in HRI Call for Papers.
Workshop: Deep Learning for Neuro-heuristic Brain Analysis
This workshop aims to explore the integration of deep learning techniques with neuro-heuristic approaches for the advanced analysis of brain data, with a particular focus on discussing how deep learning can be used to enhance our understanding of the brain as a complex self-organizing system, how its topological properties drive the interplay between sensory processing, sensorimotor integration, and cognition, and how these properties are affected by brain diseases.
ORGANIZERS: Alessandra Lintas (University of Lausanne, Switzerland), Alessandro Villa (University of Lausanne, Switzerland), Alberto Testolin (University of Padova, Italy), Marco Zorzi (University of Padova, Italy), Luca Pasa (University of Padova, Italy), Nicolò Navarin (University of Padova, Italy), Alessandro Sperduti (University of Padova, Italy)
TOPICS:
Deep learning for Neuroimaging Analysis
Deep learning for Functional Magnetic Resonance Imaging (fMRI) data analysis
Deep learning in functional near-infrared spectroscopy (fNIRS)
Deep learning models for Brain Signal Analysis
Electroencephalography (EEG) data analysis using Deep Learning
Deep learning for Brain Connectivity and Network Analysis
Functional brain connectivity analysis using Deep Learning
Structural brain connectivity analysis Deep Learning
Deep Learning for graph theoretical analysis of brain networks.
Deep learning for early detection and diagnosis of neurological disorders
Deep learning model for brain activity classification
Deep learning models for predicting cognitive states based on brain data
Brain Age Estimation using deep learning models
See details in DL4NhBA Call for Papers.
Workshop: Reservoir Computing
After the success of the first edition, the 2nd International Workshop on Reservoir Computing (RC 2024) intends to bring back together researchers to update the discussion on the state-of-the-art and the cutting-edge challenges in the field of RC, in all its declinations. These include, among the others, new models of Echo State Networks and Liquid State Machines, applications to problems of AI also in the human-centric perspective, emerging paradigms, RC for structured data, deep RC, hybrid RC/fully trained RNN models, and many more.
ORGANIZERS: Alessio Micheli (University of Pisa, Italy), Gouhei Tanaka (Nagoya Institute of Technology, Japan), Claudio Gallicchio (University of Pisa, Italy), Benjamin Paassen (University of Bielefeld, Germany), Domenico Tortorella (University of Pisa, Italy)
See details in RC 2024 Call for Papers.
Special Session: Spiking Neural Networks and Neuromorphic Computing
The special session invites contributions on recent advances in spiking neural networks. Spiking neural networks have gained substantial attention recently as a candidate for low latency and low power AI substrate, with implementations being explored in neuromorphic hardware. This special session aims to bring together practitioners interested in efficient learning algorithms, data representations, and applications.
ORGANIZERS: Sander Bohté (CWI Amsterdam, Netherlands), Sebastian Otte (University of Lübeck, Germany)
TOPICS:
Spiking Neural Network Models
Spike Response Models
Temporal Codes
Learning Algorithms for SNNs
Neuromorphic Computing
See details in SNNC Call for Papers.
Special Session: Accuracy, Stability, and Robustness in Deep Neural Networks
This special session will provide a forum for discussing simultaneous robustness to perturbations, accuracy on the test sets and generalisation, overfitting and learning from few examples in high-dimensional settings, various notions of data dimension and its benefits, and influence of the choice of network architectures (numbers of their layers and types of computational units) on accuracy and robustness of network performance. Other pressing challenges which we would like to discuss include the issue of errors, their identification and correction with provable performance guarantees, and the fundamental understanding of uncertainties and their formalisation and capture in modern learning algorithms.
ORGANIZERS: Vera Kurkova (Institute of Computer Science of the Czech Academy of Sciences, Prague, Czech Republic), Ivan Tyukin (King’s College, London, UK)
TOPICS:
Robustness and reliability of deep networks
Accuracy on test sets and generalization
Influnce of network depth on its accuracy
Stability wrt small perturbations
Learning in high-dimensional settings
Errors of neural networks and methods to reliably address them
See details in RSADNN Call for Papers.
Special Session: Antifragile dynamical systems – beyond robustness, resilience, and adaptiveness
Antifragility characterizes the benefit of a dynamical system derived from the variability in environmental perturbations and volatility. Antifragility carries a precise definition that quantifies a system’s output response to input variability and uncertainty. Systems may respond poorly to perturbations (fragile) or benefit from perturbations (antifragile). The goal of this special session is to encourage the community to consider antifragility a ”first-class citizen” beyond what dynamical systems analysis has already postulated in the robustness – resilience – adaptiveness continuum. We are happy to receive both theoretical treatments of neural networks and machine learning systems as well as applications results along the lines of the robustness – resilience – adaptiveness – antifragility spectrum
ORGANIZERS: Cristian Axenie (Nuremberg Institute of Technology, Germany), Matteo Saveriano (University of Trento, Italy), Michail Makridis (ETH Zürich, Switzerland)
See details in Antifragile Dynamical Systems Call for Papers.
Special Session: Neurorobotics
Neurorobotics brings together interdisciplinary research in machine learning, robotics and bio-inspired artificial intelligence, most prominently using artificial neural networks. After the successful Neurorobotics special session in ICANN 2023 we are announcing a second edition of this session organized under the Horizon Europe project TERAIS. We want to bring together researchers with diverse backgrounds and expertise to promote collaboration and knowledge sharing in the field of Neurorobotics and cognitive robotics for HRI.
ORGANIZERS: Igor Farkaš (Comenius University Bratislava UKBA, Slovakia), Kristína Malinovská (UKBA, SK), Andrej Lúčny (UKBA, SK), Pavel Petrovič (UKBA, SK), Michal Vavrečka (UKBA, SK), Matthias Kertzel (HiTeC, Hamburg, Germany), Hassan Ali (University of Hamburg, Germany), Carlo Mazzola (Italian Institute for Technology, Italy)
TOPICS:
Neural control and learning in robotics
Cognitive architectures for robots
Bio-inspired and developmental robotics
Human-robot interaction and collaboration
Trustworthy, human-aware and explainable robots
Computational models for robotic applications
See details in Neurorobotics Call for Papers.
Tutorial: FEDn – A scalable federated machine learning framework for cross-device and cross-silo environments
Federated machine learning has opened new avenues for privacy-preserving data analysis. Instead of pooling data in a central location, different data owners or IoT devices keep data local and training is decentralized where only
model parameters are exchanged. Despite much progress in the field, production-grade federated machine learning frameworks that deal with fundamental properties such as scalability, fault tolerance, security and performance in geographically distributed settings have not been available
to the ML-engineer. To fill this gap, Scaleout Systems and SciML at Uppsala University have designed and developed the FEDn framework. FEDn is an open-source framework dedicated to address federated machine learning challenges at scale. This tutorial aims to provide a knowledge sharing platform and highlight challenges and possible solutions related to federated machine learning.
PRESENTERS: Salman Toor (Uppsala University, Sweden), Andreas Hellander (Uppsala University, Sweden)
See details in FEDn Tutorial Announcement.