IWANN 2023
PONTA DELGADA, AZORES, PORTUGAL
JUNE 19-21, 2023
Latest news
| October 19th, 2023 | Proceedings published by Springer Part I: LNCS, volume 14134 Part II: LNCS, volume 14135 |
| July 14th, 2023 | PeerJ Award Winners |
| January 11th, 2023 | Plenary Speakers |
| January 10th, 2023 | European Projects Working Groups Creation |
| January 9th, 2023 | Early Career Researcher awards |
| September 20th, 2022 | Call for Special Sessions |
| September 16th, 2022 | First Call for Papers |
Program
- Tutorial From deep learning to deep understanding: Hands-on introduction to Deep Learning interpretability. The tutorial will include a practical session. The course will be fully implemented using Python notebooks and the cloud platform Google Colaboratory (Codes will be provided with an open GitHub repository). It is divided in: Introduction to Deep Learning models and interpretability methods (1h presentation); Hands-on tutorial (2h).
- Program of Sessions and Talks
- Book of Abstracts
- Special Sessions
Invited Plenary Speakers
 |  |
| Amaury Lendasse | Alberto Bosio |
| Metric Learning with Missing Data | Reliable and Efficient hardware for Trustworthy Deep Neural Networks |
Tutorial
From deep learning to deep understanding: Hands-on introduction to Deep Learning interpretability
Raúl Benítez. Universitat Politècnica de Catalunya
Jordi Ollé. conceptosclaros.com
Abstract: Deep learning has consolidated as the leading approach to automatically recognize complex patterns in digital images. However, although DL models typically provide higher accuracy than traditional machine learning approaches using tailored features, the resulting procedure is difficult to interpret by experts in the field. The aim of this tutorial is to provide a brief introduction to deep learning interpretability methods providing visual explanations of convolutional neural networks. The tutorial will cover state-of-the art post-hoc approaches such as saliency maps, occlusion sensitivity, gradient-based class activation mapping (gradCAM) or Local-Interpretable Model Agnostic explanations (LIME).
Platform and codes: The course will be fully implemented using Python notebooks and the cloud platform Google Colaboratory https://colab.research.google.com/. Codes will be provided with an open GitHub repository, https://github.com/
Course duration: 3 hours
Course structure:
- Introduction to Deep Learning models and interpretability methods (1h presentation)
- Hands-on tutorial (2h):
- How a CNN Works: Feature maps
- Basic visual explanations
- Comparison and take-home messages
European Projects Working Groups Creation
IWANN23 offers the possibility to meet, discuss and create new ideas around the research areas of the congress with an additional incentive of the creation of platforms acting as a driving force for strategic contributions to the European Research Area.
The main goal is to build one or more working groups with the IWANN23 members around an specific field with the final objective to create seed consortia for the development of EU proposals.
The possible partners to EU projects (Horizon Europe) are not only European countries, there are associated countries and non-associated countries with funding eligibility. See the complete list in the following link.
The workflow will be developed through a World Café conversation during the congress. See the technique in The World Cafe.
As an introduction to the European Projects Working Groups Creation café, a presentation with the main features of the recent calls and strategies to write a successful proposal will be presented. The results of the dynamics will be presented at the end of the Conference.
In order to participate in the European Projects Working Groups Creation, it will be convenient to write an “Expression of Interest (EoI)” which offers to potential applicants to any EU Artificial Intelligence related calls the opportunity to express interest in an area of research with connections to open o future calls.
The format of the EoI should be as follows:
- Name and affiliation of the responsible
- Half a page with the main interest, either
- abstract of a possible proposal, and/or
- skills provided
- List of possible calls to apply
Please, send your EoI to the IWANN mail address.
Special Sessions
SS01: Ordinal Classification
Victor M. Vargas
David Guijo-Rubio
Pedro A. Gutiérrez
Dept. of Computer Science and Numerical Analysis, University of Córdoba, Spain
Abstract
Ordinal classification is a recent area including those classification tasks in which exist a natural order between the labels, i. e. the target variable presents an ordering relation. For instance, most of health-related problems are covered by this area, since the different stages of a disease could be categorized by {“initial”, “mild”, “medium”, “severe”, “deep”}. In this way, ordinal classification techniques consider the natural order among the classes and penalize regarding the magnitude of the errors. Specific solutions have been recently proposed in the machine learning and pattern recognition literature, resulting in a very promising field. Moreover, it is also a hot topic in the deep learning field, where several approaches have been presented to the literature.
This special session aims to cover a wide range of works and recent advances on ordinal classification. We hope that this session can provide a common forum for researchers and practitioners to exchange their ideas and report their latest finding in the area.
In particular we encourage submissions addressing the following issues:
- Extensions of standard classification methods to ordinal classification (support vector machines, Gaussian processes, discriminant analysis, etc).
- Extensions of deep learning techniques to ordinal classification.
- Threshold models and decomposition methods for ordinal classification.
- Pre-processing methods for ordinal data (data cleaning techniques, feature selection, over-sampling, under-sampling, etc.).
- Evaluation measures for ordinal classification.
- Data preprocessing (feature selection, noise filtering, etc.) for ordinal classification.
- Development of novel ordinal classification frameworks.
- Time series ordinal classification (extensions of standard time series classification methods to time series ordinal classification).
- Applications in 4.0 industry, bio-medicine, renewable energies and environmental issues, economy… and any other real-world problems.
Organizers
MSc. Víctor Manuel Vargas was born in Córdoba, Spain. He received the degree of Computer Engineering from the University of Córdoba, Spain, in 2018. Then, he received his master’s degree in artificial intelligence research at the International University of Menéndez Pelayo, Spain. He is currently doing his Ph.D. thesis in advanced computing, energy and plasma. He is a member of the AYRNA group of the Department of Computer Science and Numerical Analysis of the University of Córdoba. His current research interests include deep neural networks and their applications to image classification on nominal and ordinal problems.
Dr. David Guijo Rubio received the BSc in computer science from the University of Córdoba, Córdoba, Spain, in 2016, the MSc in artificial intelligence from the International University Menendez Pelayo, Madrid, Spain, in 2017 and the Ph.D. degree in computer science and artificial intelligence from the University of Córdoba Córdoba, Spain, in 2021. He is currently a Postdoc Researcher with both the Department of Computer Science and Numerical Analysis, University of Córdoba, Córdoba, Spain and the School of Computing Sciences of the University of East Anglia, Norwich, United Kingdom. His research interests are in the areas of time series analysis (both supervised and unsupervised), and ordinal classification.
Dr. Pedro Antonio Gutiérrez received the B.S. degree in computer science from the University of Seville, Seville, Spain, in 2006, and the Ph.D. degree in computer science and artificial intelligence from the University of Granada, Granada, Spain, in 2009. He is currently an Assistant Professor with the Department of Computer Science and Numerical Analysis, University of Córdoba, Córdoba, Spain. His research interests are in the areas of supervised learning, evolutionary artificial neural networks, and ordinal classification.SS02: Machine Learning in Mental Health
SS02: Machine Learning in Mental Health
Pepijn van de Ven
Department of Electronic & Computer Engineering, University of Limerick, Ireland
Abstract
Artificial Intelligence (AI) and related data analytics have made a considerable impact on our daily lives in recent years and are now also starting to be explored in a mental health context. Whilst it is important to keep in mind that modern AI techniques are associated with considerable risks around fairness, autonomy, explicability, accountability and technical robustness, use of AI in our daily lives suggests it is here to stay and, when applied appropriately and responsibly, can result in meaningful benefits when applied to mental health interventions. This special session aims to bring together researchers from the various areas that underpin use of AI in mental health to discuss some of the key opportunities as well as issues in the application of AI to mental health. Examples of opportunities are early prediction of treatment outcomes, data-driven personalisation of interventions and the extraction of new insights from data. Examples of issues encountered in the use of AI in mental health are the perceived reduction in patient-therapist relationship, safety of AI derived decisions and recommendations, and the explainability of predictions made by AI components.
The organiser will solicit contributions from AI experts active in this field as well as mental health domain experts with the objective of providing a multidisciplinary perspective of the current and future role of AI in mental health interventions and research.
Organizer
Dr. Pepijn van de Ven is a Senior Lecturer in Artificial Intelligence and Machine Learning in the department of Electronic & Computer Engineering at the University of Limerick, Ireland. His research interests are in the application of mobile technologies and AI in mental health interventions. Recent projects include the Proactive project, a UK MRC funded research project with King’s College London, the University of Saõ Paulo and the University of Bristol. In this project Pepijn was responsible for development of the technical infrastructure used to deliver a depression intervention and to store data collected during this intervention. He is also responsible for the advanced data analytics used to analyse the data gathered during the intervention.
SS03: Neural engineering and computation: new tools and methods for studying and interacting with neural systems in both health and disease
Pablo Martínez Cañada
Department of Computer Engineering, Automation and Robotics, University of Granada, Spain
Jesus Minguillón Campo
Department of Signal Theory, Telematics and Communications, University of Granada, Spain
Abstract
For years, researchers have used the theoretical and practical tools of engineering, computer science, physics, and mathematics to understand and manipulate the nervous system. Research in neural engineering and computation extends and applies knowledge of the nervous system, from the molecular to the systems level, to develop novel neural technologies such as brain-computer interfaces, neural prostheses, and implantable devices, as well as computational modelling and imaging techniques, for the diagnosis and treatment of neurological disorders, and for other applications.
This session aims to present a collection of works that addresses the advances, challenges, and prospects in the framework of neuroengineering and computational neuroscience and their role as enablers for studying and interacting with neural systems, with a particular interest in the normal and diseased brain. This session is open, but not limited, to the following topics:
- Computational neuroscience: methods for simulation and analysis of neural circuits.
- Traditional and next-generation neural interfaces.
- Electronic design, wearable and implantable devices.
- Body area networks.
- Brain-computer interfaces.
- Functional electrical stimulation.
- Biomedical signal processing.
- Machine learning and artificial intelligence applied to biomedical data.
Organizers
Dr. Pablo Martínez Cañada, since completing his PhD in 2018 from University of Granada (Spain), has gone from holding a post-doctorate position at Istituto Italiano di Tecnologia (Italy) to becoming a Marie Skłodowska-Curie Individual-Fellowship Researcher. He has developed rigorous mathematical tools to disambiguate EEGs/MEGs and robustly interpret them in terms of specific neural features (e.g., excitation-inhibition ratio). His findings are generating important new knowledge about contributions of different neural phenomena to EEGs/MEGs and are helping quantify how neural parameters change with manipulations of neural circuits or in brain disorders. An important scientific achievement is the first co-authorship in a relevant paper on neural mechanisms of autism published in eLife, which has been selected by the Simons Foundation (USA) as the 5th most notable paper in autism research in 2020. He is now a postdoctoral fellow at the NeuroEngineering and Computing Lab (NECO Lab) of the University of Granada focused on developing methods for inferring changes in neural circuit parameters of neurodegenerative clinical conditions.
Dr. Jesús Minguillón Campos received in 2018 his Ph.D. in Information and Communication Technologies from the University of Granada. During his predoctoral stage, he worked on the design and development of non-invasive neural interfaces for the central nervous system and investigated the use of BCIs for measuring how stress affects daily-life contexts. He did a research stay at the prestigious Translational Neural Engineering Lab of Prof. Silvestro Micera (EPFL, Switzerland). During his Postdoctoral stage, he worked at the Biomedical Electronics Research Group (BERG) of the Pompeu Fabra University (Barcelona, Spain). In that stage, his research focused on wireless power transfer methods and bidirectional communication architectures for minimally invasive peripheral neural interfaces based on distributed networks of wireless injectable micro-implants with sensing and stimulation capabilities, in the framework of three European projects: eAXON (Wireless microstimulators based on electronic rectification of epidermically applied currents), SENSO-eAXON (Injectable wireless microsensors based on the eAXON technology) and EXTEND (Bidirectional Hyper-Connected Neural System). He is now a postdoctoral fellow at the NeuroEngineering and Computing Lab (NECO Lab) of the University of Granada focused on investigating next-generation neural interfaces based on massive distributed networks of wireless micro-implants, neuro-technologies for closed-loop real-time applications, and bio-signal processing for neuroscience and healthcare applications.
SS04: Deep Learning applied to Computer Vision and Robotics
Enrique Dominguez
University of Malaga, Spain
José García-Rodríguez
University of Alicante, Spain
Ramon Moreno Jiménez
Grupo Antolin S.A., Spain
Abstract
Over the last decades there has been an increasing interest in using machine learning and in the last few years, deep learning methods, combined with other vision techniques to create autonomous systems that solve vision problems in different fields. This special session is designed to serve researchers and developers to publish original, innovative and state-of-the art algorithms and architectures for real time applications in the areas of computer vision, image processing, biometrics, virtual and augmented reality, neural networks, intelligent interfaces and biomimetic object-vision recognition.
This special session provides a platform for academics, developers, and industry related researchers belonging to the vast communities of Neural Networks, Computational Intelligence, Machine Learning, Deep Learning, Biometrics, Vision systems, and Robotics, to discuss, share experience and explore traditional and new areas of the computer vision, machine and deep learning combined to solve a range of problems. The objective of the workshop is to integrate the growing international community of researchers working on the application of Machine Learning and Deep Learning methods in Vision and Robotics to a fruitful discussion on the evolution and the benefits of this technology to the society.
The methods and tools applied to vision and robotics include, but are not limited to, the following:
- Computational Intelligence methods
- Machine Learning methods
- Self-adaptation and self-organisation
- Robust computer vision algorithms (operation under variable conditions, object tracking, behaviour analysis and learning, scene segmentation, …)
- Extraction of Biometric Features (fingerprint, iris, face, voice, palm, gait)
- Convolutional Neural Networks CNN
- Recurrent Neural Networks RNN
- Deep Reinforcement Learning DRL
- Hardware implementation and algorithms acceleration (GPUs, FPGAs,…)
The fields of application can be identified, but are not limited to, the following:
- Video and Image Processing
- Video tracking
- 3D Scene reconstruction
- 3D Tracking in Virtual Reality Environments
- 3D Volume visualization
- Intelligent Interfaces (User-friendly Man Machine Interface)
- Multi-camera and RGB-D camera systems
- Multi-modal Human Pose Recovery and Behavior Analysis
- Gesture and posture analysis and recognition
- Biometric Identification and Recognition
- Extraction of Biometric Features (fingerprint, iris, face, voice, palm, gait)
- Surveillance systems
- Autonomous and Social Robots
- Robotic vision
- Industry 4.0
- IoT and Cyber-physical Systems
Organizers
Dr. Enrique Domínguez is a (full) professor in the Department of Computer Science from University of Málaga. He received his Ph.D. degree in Artificial Intelligence from University of Málaga (Spain). He has collaborated with several companies (Airzone, Fujitsu, Altra Corporacion, Fundación Andaluza de la Seguridad Social, Evita, Acerca, …) leading the computer vision workgroup of different research projects. Dominguez is author of over 50 publications, reviewer of several journals such as IEEE Trans. of Neural Networks and Learning Systems, Neurocomputing, Neural Networks, International Journal of Parallel, Emergent and Distributed Systems, Neural Computing & Applications, Optimization, etc. and an associate editor of the International Journal of Computer Vision and Image Processing (IJCVIP). In addition, he has participated chairing several special sessions or as traditional member of the program committee of several conferences such as WCCI, IJCNN, IWANN, BMIC, ICANN, ASC, EURO and others.
Dr. Jose Garcia-Rodriguez received his Ph.D. degree, with specialization in Computer Vision and Neural Networks, from the University of Alicante (Spain). He is currently Full Professor at the Department of Computer Technology of the University of Alicante. His research areas of interest include: computer vision, computational intelligence, machine learning, deep learning, pattern recognition, robotics, man-machine interfaces, ambient intelligence, computational chemistry, and parallel and multicore architectures. He has authored +150 publications in journals and top conferences and revised papers for several journals like Journal of Machine Learning Research, Computational intelligence, Neurocomputing, Neural Networks, Applied Softcomputing, Image Vision and Computing, Journal of Computer Mathematics, IET on Image Processing, SPIE Optical Engineering and many others, chairing sessions in many editions of IJCNN and IWANN and participating in program committees of several conferences including IJCNN, ICRA, ICANN, IWANN, KES, ICDP and many others.
Dr. Ramon Moreno is Engineer in Computer Science and holds a Ph.D. from the University of the Basque Country in the Computer Science and Artificial Intelligence program (2012). He has wide research experience in both national and international projects. He has worked in international research centers such as: INPE (Brazilian Space Agency), ISSSE (Robotics Group, University Paris 12), and national universities such as at UPV-EHU, CVC (Computer Vision Center – UAB), as well as technology centers: Vicomtech-BRTA, Lortek-BRTA. He has authored +50 publications in journals and top conferences and revised papers for several journals. Since 2021 he leads Big Data in the Advance Manufacturing 4.0 department in Grupo Antolin, addressing developments in Data Science, Artificial Intelligence, Computer Vision and Robotics.
SS05: Applications of Machine Learning in Biomedicine and Healthcare
Miri Weiss Cohen
Braude College of Engineering, Israel
Daniele Regazzoni
University of Bergamo, Italy
Catalin Stoean
University of Craiova, Romania
Abstract
The use of Machine learning and deep learning in biomedicine and healthcare is increasingly being used to support clinical decision-making. A variety of approaches have been developed in recent years as biomedical and healthcare data and computational capabilities have grown rapidly. These approaches have been developed in order to address emerging problems through the use of these methods. Features can be automatically extracted, classification addressed, segmentation applied, and predictive models can be generated, allowing for more efficient analysis. Machine learning is being increasingly used in human modelling, pose assessments, and the analysis of pre- and post-clinical procedures, all in the context of healthcare.
The following topics are of particular interest, but are not limited to:
- Machine and deep learning for the diagnosis of medical conditions
- Machine and deep learning based management of medical data
- Machine learning based human modelling for healthcare
- Visualization and analysis of healthcare and clinical data
- Explainable Artificial Intelligence (XAI) for biomedicine and healthcare
- Machine and Deep learning applications in biomedicine, healthcare, and rehabilitation
Organizers
Dr. Miri Weiss Cohen is a professor at Braude College of Engineering in the Department of Software Engineering. Her research interests are in the area of Machine Learning (ML) methodologies as applied to engineering problems. In recent years, she has been focusing on two major topics: first, the prediction and optimization of green energy models (solar and wind) using big data time series. Secondly, the use of CT and MRI scans to identify cancer stages and reconstruct 3D volumes utilizing Deep Learning. She is collaborating with researchers in other disciplines related to machine learning in the context of rehabilitation, human-computer interfaces and design.
Dr. Daniele Regazzoni is a professor in the Department of Management, Information and Production Engineering at the University of Bergamo. He has been conducting research in the area of virtual and physical prototyping as part of the product development process. His research interests include methods and tools for product development and optimization, digital human modelling, reverse engineering, and additive manufacturing. He specializes in engineering technologies for health, including 3D scanning, virtual and augmented reality for rehabilitation, and additive manufacturing for products that are tailored to the needs of patients. He coordinates research activities within the ING-IND/15 scientific disciplinary sector.
Dr. Catalin Stoean has a research background in evolutionary computation and intelligent systems. His research interests involve finding appropriate machine learning means to solve real-world tasks from various fields like medicine, economy and even cultural heritage. The applications he works on refer to classification of data of various types (numerical, images, text), clustering, time series modelling, image segmentation. Deep learning represents another research topic where he has activated in recent years. Catalin is a Fulbright and DAAD alumni, he received the habilitation title in Romania in 2021, he published numerous articles in prestigious journals and presented the research findings at many international conferences and universities.
SS06: Neural Networks in Chemistry and Material Characterization
Ruxandra Stoean
University of Craiova, Romania
Patricio García Báez
Universidad de La Laguna, Spain
Carmen Paz Suárez Araujo
Universidad de Las Palmas de Gran Canaria, Spain
Abstract
The application of neural networks and deep learning in the fields of chemistry and materials science is an emergent direction towards the comprehension of the chemical interactions, material structure and matter dynamics through machine learning. The practical applications to contingent domains, such as archaeology and civil engineering, add to the picture of AI support tools.
The aim of this special session is to bring together computer scientists working in applying neural network architectures to these areas, as well as chemistry and materials science engineers interested in the assistance that machine/deep learning can give in their complex tasks.
The topics targeted by this special session are as follows, but not limited to:
- Neural networks for the identification of chemical elements and mixtures from spectroscopy
- Neural networks for corrosion analysis
- Neural networks for material characterization
- Graph neural networks for chemistry and materials science
- Computational chemistry with neural networks
- Deep learning for image processing in cultural heritage
- Deep learning for civil engineering
Organizers
Dr. Ruxandra Stoean is Associate Professor at the University of Craiova, Romania, and Principal Investigator at the Romanian Institute of Science and Technology, Cluj-Napoca, Romania. She holds a PhD in computer science, focused on optimization through evolutionary computation. Her current research interests involve the development of deep learning models for images and signals, with applications in medicine, engineering and cultural heritage. She serves as Academic Editor for the Plos One journal.
Dr. Patricio García Báez is Assistant Professor in Computer Science and Artificial Intelligence at the Universidad de La Laguna, Spain. He teaches courses related to Artificial Intelligence and Artificial Neural Networks. His research is focussed on the field of Artificial Neural Networks which has led him to publish several articles in national and international level and contribute to the participation and organization of various conferences and seminars. The focus areas of his works are the design of new neural architectures and application in the field of clinical diagnosis and the processing of biological and environmental signals.
Prof. Carmen Paz Suárez Araujo is Professor of Computer Sciences and Artificial Intelligence at the Universidad de las Palmas de Gran Canaria (ULPGC). She is BS & MS in Physics and PhD in Computer Sciences. She has been Director of Intelligent Computing, Perception and Big Data Research Group of ULPGC and currently she is Head of Computational Neuroscience Research Division at the Institute of Cybernetics Science and Technology of the ULPGC. She has been Director of PhD. Program of Neural Computing in Natural and Artificial Systems of the same University. She has been Vice-Rector of the ULPGC, Vice-Dean of the Faculty of Computer Sciences of this University for many years.
She has been Invited Professor in a broad range of foreign Universities, around 30, with longer research stays in several of them: the University of Florida, Universidade de Lisboa, Comenius University, visiting professor during a year, at the University of Technology Sydney (UTS) and University of Arizona.
She has an extensive research experience focused in the knowledge of the brain structure and function and designing models and computational systems with some brain capacities and intelligent systems for decision-making, with more than 140 scientific articles and book chapters, and more than 150 contributions to international and national congresses. Her research lines are • Natural and Artificial Neural Networks. Design of New Neural Architectures; •Application of Neural Computation in Clinical and Environmental Domains, Biomedicine, Neuroinformatics and Bioinformatics; •Computational Neuroscience and Cognitive Computation: Neural communication models and learning.
The mid-to-long term scientific-technical interests and objectives of the research agenda are focused on improving intelligent computing models to analyse clinical data and to reach accurate and reliable early diagnosis of AD and differential diagnosis of dementia, and also effective computational tools for translational medicine and personalized medicine, in the scope of brain disease & the COVID-19. Other important objective is to determine the big cross-relation between intelligent computing and Chemistry and Material Science.
Her research work has been awarded for Spanish and international institutions (Spain Real Doctors Academy, The CAN of Sciences 2020, amongst others).
SS07: Real World Applications of BCI Systems
Ivan Volosyak
Rhine-Waal University of Applied Sciences, Germany
Abstract
A Brain-Computer Interface (BCI) is based on the analysis of brain activity to provide a non-muscular channel for detection of user intentions and sending commands to the external world. A BCI emerged few decades ago as a novel way of communication allowing subjects with severe disabilities, who may be completely paralyzed or locked-in, to communicate and to interact with the surroundings and outer world. Modern BCI applications can also be used in very different areas (e.g. gaming and entertainment industry). In the future, a qualitative improvement in performance is expected, in terms of substantially higher information transfer rates (ITRs) and reliability with potential users in emerging areas of interest.
The main goal of this special session is to show the last research advances in neurotechnologies, BCI paradigms, various real-world BCI applications, as well as innovative signal processing algorithms, training techniques or paradigms that make them possible.
Organizer
Dr. Ivan Volosyak received the Diploma in the field of automation and control of technical systems from the Dnepropetrovsk State University, Dnepropetrovsk, Ukraine, in 1998, and the Ph.D. degree in electrical engineering from the University of Bremen, Bremen, Germany, in 2005. He is currently a Professor for Biomedical Engineering at the Rhine-Waal University of Applied Sciences, Kleve, Germany. Previously, he was a Postdoctoral Research Fellow at the Institute of Automation, University of Bremen, and Project Manager of several national and the European Union projects carried out at the University of Bremen, Germany. From 2005 to 2008, he has held visiting positions at the Institute for Knowledge Discovery, Graz University of Technology, Austria, and at the Centre for Rehabilitation Engineering, Glasgow University, U.K. His research interests include brain-computer interfacing, signal processing, digital image processing, service robotics, and assistive technology with the primary focus on applications in spinal cord injury rehabilitation.
SS08: Spiking Neuron Networks: Applications and Algorithms
Elisa Guerrero Vázquez
Fernando M. Quintana Velázquez
Universidad de Cádiz, Spain
Abstract
Spiking Neuron Networks (SNNs) and Neuromorphic Systems are often referred to as the third
generation of neural networks. Highly inspired from natural computing in the brain and recent advances in neurosciences, they derive their strength and interest from an accurate modelling of synaptic interactions between neurons, taking into account the time of spike firing. SNNs overcome the computational power of neural networks made of threshold or sigmoidal units. Based on dynamic event-driven processing, they open up new horizons for developing models with an exponential capacity of memorizing and a strong ability to fast adaptation. As they are mimicking real neurons behaviour, they allow a massively parallel, low power calculation, which is highly suitable for embedded computation.
This special session aims at approaching this paradigm to all the IWANN community, to share visions on the intersection between classical neural networks, deep learning and neuromorphic computation. Topics of interest include but are not limited to:
- Deep SNN
- SNN computational models
- Online and Local learning
- Neuromorphic systems design
- Computer Vision and SNN
- Other emerging applications
Organizers
Dr. Elisa Guerrero Vázquez, is an Associate Professor at the University of Cádiz (UCA), in the Department of Computer Engineering (DCE), and in the TIC-145 Research Group: Intelligent Computing Systems. The main areas of research focus on the areas of Machine Learning, Model Selection and Computer Vision, maintaining a highly relevant multidisciplinary collaboration in the field of Nanotechnology, which has provided greater experience and a great diversity of high-quality work with scientific impact. Currently she supervises (IP) Spanish national research project NEMOVISION: Sistemas Neuromórficos para Visión Artificial.
Fernando M. Quintana Velázquez is a PhD student at the University of Cádiz (UCA). In 2019 he got a 4- years fellowship from the Spanish ministry of Science, Innovation and Universities. He is currently doing a stay at the Institute of NeuroInformatics (INI), University of Zurich and ETH Zurich, Switzerland. His main areas of research focus on Neuromophic systems, Spiking Neural Networks, Meta-learning and Local online learning.
SS09: Deep Learning and Time Series Forecasting: Methods and Applications
Francisco Martínez Álvarez
Universidad Pablo de Olavide, Spain
Verónica Bolón Canedo
Universidade da Coruña, Spain
David Camacho
Universidad Politécnica de Madrid, Spain
Abstract
On the one hand, time series can be found in almost all disciplines nowadays. Thus, time series forecasting is becoming a consolidated discipline that provides meaningful information in a wide variety of areas, turning their efficient analysis into the utmost relevance for the scientific community.
On the other hand, deep learning has become one of the most powerful and successful strategies to extract information from large datasets. Many researchers are now developing their models based on deep learning, being applied to almost all disciplines as well.
This session pays attention to the extraction of useful knowledge from time series with deep learning. The analysis of very large time series, given its relevance in the emergent context of big data, is also encouraged. The submission of papers including both novel methods and relevant applications is encouraged.
Topics of interest for the special session include but are not limited to:
- New approaches based on deep learning for big data time series forecasting.
- Hybrid deep learning systems for time series forecasting.
- Ensemble deep learning approaches for time series forecasting.
- New explainable artificial intelligence models for time series forecasting with deep learning.
- Deep transfer learning for time series forecasting.
- Application of deep learning to sound real-world problems.
Organizer
Dr. Francisco Martínez Alvárez‘s most remarkable achievements have been done in the field of Artificial Intelligence, Data Mining and Big Data and, obviously, Deep Learning with a great diversity of tools and algorithms developed in different areas: classification, pre-processing, regression and, especially, in the prediction of time series. Such algorithms have been successfully applied to different fields like smart grids, environment, remote sensing and seismic engineering. An important characteristic of all the research he has carried out is that it has been continuously applied to real problems in society. Thus, problems as diverse as the prediction of natural disasters, air pollution, remote sensing or renewable energies have been addressed. In addition, most of the work has been done in close collaboration with the private sector and, therefore, the transfer of knowledge to industry has been ensured thanks to the software and actions developed.
Dr. Verónica Bolón-Canedo has been working on artificial intelligence and machine learning since 2009. After a postdoctoral fellowship in the University of Manchester, UK (2015), she is currently an Associate Professor in the Department of Computer Science and Information Technologies of the University of A Coruña. She has co-authored two books, seven book chapters, and more than 100 research papers in international conferences and journals. She co-organized several special sessions at international conferences, such as ESANN and IJCNN, and served in program and scientific committees. Her current research interests include machine learning, deep learning and big data. She has served as Secretary of the Spanish Association of Artificial Intelligence and is member of the Spanish Young Academy and the Royal Academy of Sciences of Spain.
Dr. David Camacho is full professor at Computer Systems Engineering Department of Universidad Politécnica de Madrid (UPM), and the head of the Applied Intelligence and Data Analysis research group (AIDA: https://aida.etsisi.uam.es) at UPM. He holds a Ph.D. in Computer Science from Universidad Carlos III de Madrid in 2001 with honors (best thesis award in Computer Science). He has published more than 300 journals, books, and conference papers. His research interests include Machine Learning (Clustering/Deep Learning), Computational Intelligence (Evolutionary Computation, Swarm Intelligence), Social Network Analysis, Fake News and Disinformation Analysis. He has participated/led more than 50 research projects (National and European: H2020, DG Justice, ISFP, and Erasmus+), regarding to the design and application of artificial intelligence methods for data mining and optimization for problems emerging in industrial scenarios (coal mining, steel), aeronautics, aerospace engineering, cybercrime/cyber intelligence, social networks applications, or video games among others. He serves as Editor in Chief of Expert Sytems from 2023, and he is an Associate Editor of several journals including Information Fusion and Cognitive Computation.
SS10: ANN HW-Accelerators
Mario Porrmann
Osnabrück University, Germany
Ulrich Rückert
Bielefeld University, Germany
Abstract
Artificial neural networks (ANNs) are simple models of abstract brain-like computing principles performing massively parallel computations for artificial intelligence tasks. As the performance increase of microprocessors slowed down, the demand for application-specific solutions for ANN architectures is increasing in applications like autonomous driving, cognitive robotics, cognitive edge computing, and Internet-of-Things. Many analogue, digital and mixed analogue/digital chip implementations have been proposed in the last 40 years. In nanoelectronics, the growing complexity of ultra-large-scale integration turns difficult problems (e.g., power, reliability, testing, connectivity, design complexity, design support, …) into great challenges. Because of these challenges, digital implementations are dominating today.
In this special session, recent hardware implementations for ANNs will be discussed. Nowadays, the number of chip proposals from academia and companies (from start-ups to enterprises) is heavily increasing. The focus is on ANN models such as Deep Neural Networks, Long Short-Term Memory, and Auto-Encoder Networks, which are mainly used in applications today. Their performance will be compared to ANN implementations on commercial off-the-shelf chips like multi-core chips, graphics processing units, and field-programmable gate-arrays. Based on current applications, future requirements for ANN HW accelerators will be estimated.
Organizers
Dr. Mario Porrmann is professor and head of the “Computer Engineering” group at Osnabrück University, Germany, since April 2019. He graduated as “Diplom-Ingenieur” in Electrical Engineering at the University of Dortmund, Germany, in 1994. In 2001, he received a PhD in Electrical Engineering from the University of Paderborn, Germany, for his work on “Performance Evaluation of Embedded Neurocomputer Systems”. From 2010 to March 2012, he was Acting Professor of the “System and Circuit Technology” research group at the Heinz Nixdorf Institute, University of Paderborn. He then joined the research group “Cognitronics and Sensor Systems” in the Center of Excellence “Cognitive Interaction Technology” at Bielefeld University as Academic Director. Mario Porrmann’s scientific work focuses on resource-efficient computing with a special emphasis on adaptive heterogeneous architectures for embedded systems and cognitive edge computing.
Dr. Ulrich Rückert studied Computer Science (Dipl. Inf.) and received a Dr.-Ing. degree in Electrical Engineering from the University of Dortmund, Germany (1989). From 1992 to 1995 he was Associate Professor at the Technical University of Hamburg-Harburg, Germany. In 1995 he joined as a Full Professor the Heinz Nixdorf Institute at the University of Paderborn, Germany, heading the research group ‘‘System and Circuit Technology’’. Since 2009 he is Professor at Bielefeld University, Germany heading the “Cognitronics and Sensor Systems” group of the “Cluster of Excellence – Cognitive Interaction Technology”. He is working on innovative circuit design and development of nanoelectronic systems for massively parallel and resource-efficient information processing. His main research interests are bio-inspired architectures for nanotechnologies and cognitive robotics.
Early Career Researcher IWANN 2023 awards by PeerJ Publishing
As a part of a successful collaboration between IWANN 2023 and PeerJ Publishing, two awards are offered:
- Best poster
- Best presentation
The recipients must be early career researcher (PhD student or up to 4 years postdoc) who authors a full paper, attends the Conference and presents the poster or talk.
The winners will be invited to submit a substantial extension of their papers to the PeerJ Computer Science journal. If accepted, the publication(s) will have Article Processing Charges waived. PeerJ Publishing also features award winners on their blog site and interviews them regarding their research.
You are cordially invited to read the interview with Shih-Kai Hung, winner of the Early Career Researcher IWANN 2021 award, at PeerJblog.
First Call for Papers
On behalf of the Organizing Committee of the 17th International Work-Conference on Artificial Neural Networks (IWANN2023), we are pleased to invite you to participate in this event that will be held in June 2023 in Ponta Delgada (Sao Miguel, Azores Islands, Portugal). This gathering will bring people physically together again after 4 years in the one of the most beautiful Atlantic’s islands, conducive to creativity and inspiration.
This biennial meeting seeks to provide a discussion forum for scientists, engineers, educators and students about the latest discoveries and realizations in the foundations, theory, models and applications of systems inspired by nature, as well as in emerging areas related to the above items, using computational intelligence methodologies. As in previous editions, we strongly emphasize the wide range of topics comprised under the umbrella of IWANN2023 and, in particular, we focus on trending topics such as Deep Learning and Ethics in AI. It’s confirmed one tutorial about “From Deep Learning to Deep Understanding”.
We present below a non-exhaustive list of areas of interest for the congress to get a flavour of the IWANN23’ orientation:
- Mathematical and theoretical methods in computational intelligence
- Deep Learning
- Learning and adaptation
- Emulation of cognitive functions
- Bio-inspired systems and neuro-engineering
- Advanced topics in computational intelligence
- Agent based models
- Time series forecasting
- Robotics and cognitive systems
- Interactive systems and BCI
- Machine Learning for 4.0 industry solutions
- AI Health
- AI in 5G technology
- Social and Ethical aspects of AI
- General Applications of AI
The approach will be both theoretical and practical, through invited talks, tutorials, workshops, posters, presentation of demos and functional prototypes. Besides, we offer the possibility to carry out a limited number of virtual presentations for those who want to participate but have serious difficulties to travel. The proceedings will include all the presented communications to the conference. As in previous editions of IWANN, we are arranging the publication of the proceedings with Springer-Verlag as Lecture Notes in Computer Science (LNCS) series, and the books will be available shortly after the Congress in order allow the authors to incorporate suggestions and improvements from the presentations. It is also foreseen the publication of extended versions of selected papers in special issues of several prestigious journals. Previous congresses led to special issues of Neural Computing and Applications, Plos One and Neural Processing Letters. We are working to have at least the same collaborations.
International Steering Committee
| Davide Anguita | Università degli Studi di Genova | Italia |
| Andreu Catalá | Universitat Politècnica de Catalunya | Spain |
| Marie Cottrell | Université Paris 1 Panthéon-Sorbonne | France |
| Gonzalo Joya | Universidad de Málaga | Spain |
| Kurosh Madani | Université Paris-Est Créteil | France |
| Madalina Olteanu | Université Paris Dauphine – PSL | France |
| Ignacio Rojas | Universidad de Granada | Spain |
| Ulrich Rückert | Universität Bielefeld | Germany |
Technical Assistant Committee
| Miguel Atencia | Universidad de Málaga |
| Francisco García-Lagos | Universidad de Málaga |
| Luis Javier Herrera | Universidad de Granada |
| Luís Mendes Gomes | Universidade dos Açores |
| Fernando Rojas | Universidad de Granada |