Inspired by Andrew Trask's article about coding a neural network in 11 lines of Python, I wondered if this could be accomplished as succinctly in JavaScript. Part of the brevity of the Python solution is the use of a common numeric library called Numpy which helps manipulate matrix mathematics. For something comparable, I rolled my own JavaScript matrix library to assist with some of the notation and computation. The implementation converges quickly on the XOR solution as represented by the box moving toward the outlined target.
Explore the solution on the newly revamped OpenProcessing website and embedded here:
20161112 Update: Just noticed this similar implementation.
"The only reason for time is so that everything doesn't happen at once." -Albert Einstein
20161102
Neural Network in 12 lines of JavaScript
Labels:
Computing
,
Mathematics
,
Observed
,
Unit Operations
Subscribe to:
Post Comments
(
Atom
)
KVR News:
- CARP Audio updates Body Shifter for Mac and Windows
- Sound Magic updates Neo Piano (v2.2), Acoustic Guitar (v1.2) and China Ensemble (v1.3)
- WesAudio Releases _MIMAS Gemini 500 Series FET Stereo Compressor
- Softube Releases Vocal Tuner & Deesser Plug-ins
- Behringer Releases 2-XM - Analogue Eurorack Module Based on the Oberheim SEM
The Gadget Blog | Latest Gadgets, Technology
Error loading feed.
No comments :
Post a Comment