~/talk

Making VR More Interesting With JavaScript and Machine Learning

Talkat JSConf Korea 2020 Home Edition · on Sunday, 2020-09-20· [webxr]
slides:none on file

Starts from a plain A-Frame HTML file and uses Node/Express as a backend. Uses Brain.js neural network built with three hidden layers trained on arrays of user records (x y z position steps foundItem → finish likelihood). Training is one method call, demo shows it working: if likelihood is high items move farther away, if low they move closer so players find one. Live demo and code confirm the system runs in real time.

AI-written summary · about

  1. 0:00Start
  2. 0:36Overview
  3. 1:10Background on VR
  4. 10:27Neural Networks
  5. 11:16Brain.js
  6. 12:23Choosing Features What will add the most value for a user?
  7. 20:10Other Considerations
  8. 22:34Key Takeaways
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.