Workshops

    • Interactive Explanations of Neural Networks and Artificial Intelligence (Int-XAI)

      Deep learning architectures have become synonymous with state-of-the-art performance across a broad spectrum of domains. In everything from natural language processing and generation for conversation, to machine vision for clinical decision support, intelligent systems are supporting both the personal and professional spheres of our society. Explaining the outcomes and decision-making of these systems remains a challenge. As the prevalence of AI grows in our society, so too does the complexity and expectation surrounding the ability of autonomous models to explain their actions.

      https://sites.google.com/view/int-xai2023/call-for-papers

      • Prof Nirmalie Wiratunga
      • Dr John Isaacs
      • Dr Kyle Martin
      • Dr Anjana Wijekoon
    • Machine Learning, Artificial Intelligence and Neural Networks in Higher Education Workshop

      This workshop aims to explore applications of Machine Learning, Artificial Intelligence (AI) and Neural Networks in Higher Education (HE). It will include presentations/talks related to areas such as AI technologies utilised to support teaching and learning, intelligent tutors, personalised learning, administrations of educational systems, educational research, augmented and virtual reality.

      • Chrisina Jayne

        Teesside University, UK

        Technical Co-Chair

      • Danilo Mandic

        Imperial College London

      • Carlos Moreno-Garcia

        Robert Gordon University, UK

        Workshop Co-Chair

      • Eyad Elyan

        Robert Gordon University, UK

        Publicity Co-Chair

    • Multimodal Synthetic Data for Deep Neural Networks (MSynD)

      The use of synthetic data in training and evaluating deep neural networks has become increasingly popular in recent years, due to its ability to provide large amounts of diverse and customizable data for training and testing. Traditional training data are mostly collected from real world scenarios which make them expensive, time-consuming to acquire, and often require expert knowledge for annotation. Synthetic data on the other hand is artificially generated and has the advantage of being easily controllable and scalable, making it possible to generate large amounts of data for a wide range of tasks, without compromising the privacy of individuals or commercial interests. In addition to this, synthetic data provide a unified labelling framework that can be exploited for multi-task learning. However, many current approaches to synthetic data generation and application focus on single modalities, such as audio, video, text, and sensor data, and do not adequately capture the multimodal nature of many real-world data sets. In this workshop, we propose to explore the challenges and opportunities of using synthetic data in multimodal deep learning applications. We are aiming to bring together researchers and practitioners from a variety of academic and industrial disciplines to discuss the recent advances in multimodal synthetic data generation, and to showcase successful examples of their usage in deep neural network applications. Attendees will have the opportunity to learn about the latest techniques and tools for generating and using synthetic data, and to apply these techniques to their own research problems. This workshop is intended for researchers and practitioners working in the fields of deep learning and artificial intelligence.

      Link: https://research.csiro.au/icv/multimodal-synthetic-data-for-deep-neural-networks-msynd-workshop/

      • Moshiur Farazi
      • Olivier Salvado
      • Zeeshan Hayder
      • Mohammad Ali Armin
      • Xun Li
      • Ali Cheraghian
    • Workshop on Trustworthy and Responsible AI: theory, applications, and challenges

      Emerging as a pivotal technique supporting a wide range of societal activities, such as autonomous transportation and health care, a trustworthy and responsible machine learning system (TRMLS) has become a focus for worldwide researchers. One main goal is to investigate the different principles and constraints for TRMLS to be applied in practice by a broad spectrum of researchers and practitioners. This workshop will focus on discussing the theories, principles, and experiences of developing trustworthy and responsible machine learning systems. This workshop will be the first attempt of gathering researchers interested in the emerging and interdisciplinary filed of trustworthy and responsible machine learning from a wide range of disciplines. This workshop will highlight the recent related works and foster unprecedented chance to bridge the research gaps across the topics of machine learning, security, fairness, privacy and so on. This workshop will conduct a reflection on foundations (theory and application) of trustworthy machine learning and lay out a positive vision for future collaboration and research activities.

      • Dr. Qinghua Lu
      • Dr. Dong Yuan
      • Dr. Xuyun Zhang
      • Dr. Feng Liu
      • Dr. Minhui Xue
      • Dr. Miao Xu
      • Dr. Yanjun Zhang
      • Dr. Huaming Chen
    • Autonomous Learning in Complex Decision Situations

      The aim of the workshop is to create an integrated and holistic computational foundation for a new research direction – autonomous learning in complex decision situations. We define a decision situation as complex if the data available for use in machine learning efforts is massive and/or uncertain and/or dynamic. Autonomous learning will advance the capability of machines to learn from complex situations and minimise human involvement in the learning process (such as to autonomously determine a threshold, a sample set, a source domain, a concept drift, and a policy). Recently we have seen several new successful developments in the direction, such as massive stream learning algorithms, incremental and online learning for streaming data. These developments have demonstrated how the autonomous learning can be used in some complex decision situations to contribute to the implementation of machine learning capability. We have also witnessed some compelling evidence of successful investigations on the use of the autonomous learning methodology to support real-time prediction and decision making in practice. With these observations, it is instructive, vital, and timely to offer a unified view of the current trends and form a broad forum for the fundamental and applied research as well as the practical development of autonomous learning in complex decision situations for improving machine learning and data-driven decision support systems.

      • Luis Martínez
      • Ivor W Tsang
      • Jie Lu
      • Dr. Feng Liu
      • Jun Wang
      • Xin Yao

        Southern University of Science and Technology (SUSTech), Shenzhen, China,

    • Special INNS Workshop: International Neural Network Society Workshop on Deep Learning Innovations and Applications

      INNS DLIA 2023

      This special INNS sponsored workshop aims to explore innovations and applications
      of deep Learning and bring together academic researchers and industry
      professionals. Authors will be invited to submit a paper in the first edition of the INNS
      workshop series in Procedia Computer Science,
      https://www.sciencedirect.com/journal/procedia-computer-science which is open
      access.

      Topics for the workshop include

      - Deep Learning Applications in the areas such as healthcare, finance, education, visual recognition, entertainment, personalisation, fraud detection,
      autonomous driving, bioinformatics and others
      - Graph Neural Networks
      - Reinforcement learning
      - Generative Neural Networks
      - Deep Neural Networks for computer vision
      - Deep Neural Networks for natural language processing
      - Deep learning and ethics
      - Explainability and emerging issues

      The workshop will be entirely online with links to the presentations and abstracts of
      the accepted papers.

      View Additional Information
      Please go to the Workshop Website to Download the Paper Template Information: https://neural.memberclicks.net/ijcnn-2023-inns-dlia-workshop
       

      • Chrisina Jayne

        Teesside University, UK

        Technical Co-Chair

      • Danilo Mandic

        Imperial College London

      • Richard Duro

        Universidade da Coruña, Spain

        Award Co-Chair