Challenges
Workshop Challenge 1. HD/VSA programming framework Architectures.
Description: Denis Kleyko is planning to share his experience of contributing to HD/VSA library — Torchhd. Next, the idea is to discuss in groups and identify programming primitives/functionality, which would make your daily work with HD/VSA easier. This discussion will take place on Friday June 16 at 15:00. We are still preparing the exact formulation for the discussion so more details might come later.
Workshop Challenge 2. HD/VSA as a scientific/engineering discipline. This challenge will be discussed during the Midnight Session of the MIDNIGHTVSA workshop and the final webinar of VSAONLINE on Thursday June 15, 22:00 (20:00 GMT).
Description:
After more than three decades of active research on HD/VSA there are strong indicators of their unique place within the AI landscape. A whole generation of PhDs have graduated with HD/VSA at the heart of their projects. There are several high-profile academic projects, which have been going over the past few years. We see an emergence of stable constellations of researchers all over the world focusing on different aspects of HD/VSA. In other words, HD/VSA is on its way to become a discipline of its own within the AI landscape.
However, several challenges need to be addressed in order to make HD/VSA to be a discipline that is both accepted and recognized by other communities as well as being attractive for a new generation of researchers. These challenges, as we see, come along several dimensions:
How to make HD/VSA attractive for academic and industrial employers?
What unique skills do researchers trained within HD/VSA posses?
How these skills are matched to the ones that are common within the todays mainstream AI?
How to make HD/VSA attractive for the newcomers - undergraduate students, graduate students, postdocs, and researchers from other disciplines.
Pre-requisite skills?
A clear career path including the guidelines on the publication track?
Why bother at all? – the selling point
How to make HD/VSA attractive to and understood by other disciplines, e.g., from the applications point of view?
What are these OTHER disciplines, which would benefit from or be beneficial to HD/VSA?
Neuroscience?
Deep learning?
Material science?
Electrical engineering?
Neuromorphic computing?
Cognitive science?
Computer science?
Robotics?
What else?
What kind of outreach activities (in addition to ongoing webinars, website, community workshops, tutorials on conferences for other communities) are needed? What are the relevant conferences to be present on?
We are planning to bring these items for discussion on the final for this season session of VSAONLINE on Thursday June 15 at 20:00 GMT. This will be a hybrid event attended in-person by 25 participants of the MIDNIGHTVSA workshop in Luleå, Sweden.