~/talk

Everyday AI

on YouTube 32m
Talkat Framework Summit 2018 · 2018-10-02..10-03· [ai-assisted-development]

speaker

name:Asim Hussain
website:https://asim.dev

resources

video:https://youtu.be/Q9uQBFbQhWo
slides:none on file

summary

A demo called moji fire takes a photo, finds facial landmarks, feeds them to a small neural net and swaps in emoji using the Azure Face API; it runs as a Twitter bot (shadow-banned) and now a Slack bot. Browser ML uses tensorflow.js and pretrained MobileNet (trained on ~1000 classes) so image classification happens client-side. GANs (pix2pix / generator+discriminator) create images after heavy cloud training; exported generator models can be ~13 MB and run in the browser.

AI-written summary · about

chapters (11)

  1. 0:00Intro
  2. 1:13Meet Asim Hussain
  3. 1:51Asims Journey
  4. 4:00mojifire
  5. 6:54neural networks
  6. 9:57neural network animation
  7. 14:14tensorflow mobile net
  8. 16:32tensorflow JS
  9. 20:39Azure API
  10. 22:50Summary
  11. 30:19GANs

related talks

~/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.