- Evolving neural networks for POMDP tasks
- Evolutionary neural architecture search
- Evolutionary surrogate-assisted optimization
Beyond Backpropagation: Cognitive Architectures for Object Recognition in Video
Jose C. Principe, Ph.D.
Distinguished Professor and Eckis Chair of Electrical Engineering
University of Florida, USA
Backpropagation has been the hallmark of neural network technology, but it creates as many problems as it solves, because it leads to a black box approach, the difficulty of optimizing hyperparameters and the lack of interpretation, and explainability so important in practical applications. We have devised a new way to train deep networks for classification without error backpropagation, with guarantees of optimality under some conditions. This talk presents an overview of this recent advance, illustrates performance in benchmark problems, and advantages for transfer learning.
Lecture I – Requisites for a Cognitive Architecture
- Processing in space
- Processing in time with memory
- Top down and bottom processing
- Extraction of information from data with generative models
- Attention mechanisms and fovea vision
Lecture II – Putting it all together
- Empirical Bayes with generative models
- Clustering of time series with linear state models
- Information Theoretic Autoencoders
Lecture III – Beyond Backpropagation: Modular Learning for Deep Networks
- Reinterpretation of neural network layers
- Training each learning without backpropagation
- Examples and advantages in transfer learning
Jose C. Principe (M’83-SM’90-F’00) is a Distinguished Professor of Electrical and Computer Engineering and Biomedical Engineering at the University of Florida where he teaches statistical signal processing, machine learning and artificial neural networks (ANNs) modeling. He is the Eckis Professor and the Founder and Director of the University of Florida Computational NeuroEngineering Laboratory (CNEL) www.cnel.ufl.edu . His primary area of interest is processing of time varying signals with adaptive neural models. The CNEL Lab has been studying signal and pattern recognition principles based on information theoretic criteria (entropy and mutual information). The relevant application domain is neurology, brain machine interfaces and computation neuroscience.
Dr. Principe is an IEEE Fellow. He was the past Chair of the Technical Committee on Neural Networks of the IEEE Signal Processing Society, Past-President of the International Neural Network Society, and Past-Editor in Chief of the IEEE Transactions on Biomedical Engineering. He received the IEEE Neural Network Pioneer Award in 2011. Dr. Principe has more than 800 publications. He directed 99 Ph.D. dissertations and 65 Master theses. He wrote in 2000 an interactive electronic book entitled “Neural and Adaptive Systems” published by John Wiley and Sons and more recently co-authored several books on “Brain Machine Interface Engineering” Morgan and Claypool, “Information Theoretic Learning”, Springer, and “Kernel Adaptive Filtering”, Wiley.
The ACDL 2020 Lectures of the Professor Mihaela van der Schaar:
- Machine Learning for Medicine – a new research frontier
- Causal Inference and Estimating Individualized Treatment Effects
- From Black Boxes to White Boxes: Machine Learning Interpretability, explainability and Trustworthiness
ACDL 2020 an On-Site & On-Line Event!
After numerous discussions, we have concluded that holding the event this year in mixed form both in presence (like previous editions) and virtual is more advantageous than postponing it until next year.
In order to accommodate a large number of situations, we are offering the option for either physical presence or virtual participation. We would be delighted if all participants manage to attend, but are aware that special circumstances are best handled by having flexible options.
The advanced course, hence, will be held in presence with virtual rooms for participants using remote connection (e.g., Zoom or MS Teams). The online lectures (e.g., live presentations and/or recorded ones) will be made possible.
See you (physically or virtually) in Tuscany in July!
We expect that the situation will be improved sufficiently in July to continue with the ACDL advanced course as planned. We are monitoring the developments and will announce any changes on this website if necessary.
Ticket Registration is open.
Please stay tuned for further updates.
Call for Virtual Rooms and Socials
ACDL 2020 will continue to support the strong community-building role that is so central to the conference. We hope to create opportunities for all participants to meet new people and to share knowledge, best-practices, opportunities, and interests. To enable this, we will support several virtual rooms and socials.
A virtual room or social is a participant-led video-driven meeting centred around different themes. These themes can be anything ranging from:
- A gathering around research topics and interests (e.g., artificial intelligence, generative models, reinforcement learning, deep learning, big data, covid-19, social impact AI, ML, data science),
- Around skills exchange and training (e.g., giving better presentations, guidance on academic job applications), supporting affinity group meetings (e.g., QueerInAI, Women in Machine Learning),
- Or other social and intellectual gatherings (e.g., 1st virtual conference, book club).
We will list these events on the ACDL 2020 webpage with a link the video session, and include it in the calendar of events and support its publicity.
- If you are interested in hosting a virtual room/social, please send a detailed email to firstname.lastname@example.org
- Virtual rooms are typically 2-hour long video sessions, must have two leads (who will organise the session, moderate the session, and ensure respectful communication). Organisers and guests should be registered participants of ACDL 2020.
- Submit this form before 18 May 2020 (anywhere on earth).
- We will review these as quickly as we can after the deadline. We may combine activities, or suggest other modifications (such as suggesting alternative dates/times) in order to balance the programme of activities.
Code of conduct: Being part of ACDL 2020, social events are subject to the general code of conduct of the meeting.
- Deadline: 18 May 2020.
- Notification: 20 May.
ACDL 2020 is proceeding as planned for July in Certosa di Pontignano, Tuscany. Like you, the organizing committee is actively monitoring the global situation regarding the spread of SARS-CoV-2. We are aware of the risks of large gatherings, especially those that attract attendees from around the world such as our advanced course. We are actively exploring options and developing alternative plans should a change in ACDL 2020 be warranted.
Currently, we are working to provide the possibility of remote presentation for speakers who are unable to travel due to restrictions imposed by their countries in light of the SARS-CoV-2 pandemic.
Should the situation change, it may become necessary to move to 100% virtual course. In this case, the registration will be reduced and participants refunded accordingly.
All updates will be shared in a timely manner via our website, through email to authors of accepted papers, and via social media.
We are looking forward to seeing you at ACDL 2020 (Certosa di Pontignano, Tuscany).
ACDL 2020 Organizing Committee .