~/talk

Neural Networks and Machine Learning Building Intelligent Angular Applications

Talkat Angular Connect 2016 · 2016-09-27..09-28· [angular, machine-learning]
slides:none on file

A small Angular app implements a hand‑rolled neural net (a 2‑3‑1 network), runs backpropagation with per‑example or batch updates, and trains on XOR until the predicted outputs match the targets. Implementation exposes weights and biases, saves a JSON snapshot of weights to import a pretrained state, and demonstrates a browser demo that mostly works (occasional local minima require more epochs). Mentions TensorFlow/brain.js as alternative libraries and the core claim that training is just updating weights and biases.

AI-written summary · about

  1. 0:00Intro
  2. 0:26About me
  3. 1:53What is Neural Networks
  4. 5:58Feedforward Neural Networks
  5. 14:29Demo
  6. 14:59Neural Network
  7. 17:59Intelligent Apps
  8. 21:14Snapshots
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 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
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
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.