17 Jul 2015

Learn

I’m just about to wrap up a weeks vacation before it’s back on the horse again – as I leave for the nucl.ai conference Sunday morning. If you’re going, maybe I’ll see you there? If not, you should go check out the live stream.

Basis

Anyway, so in my vacation I built a little project when I could find a bit of time here and there. It was inspired by work on a client project earlier in the year, where we looked at wiring up a neural network for analysis of a noisy sensor.

The problem at the time was that although I could find a few C# NN libraries here and there, they were either not really a good fit or had a not-so-open open-source license like GPL (good thing I don’t have comments enabled here, eh?).

Anyway, that felt a bit silly, so I figured that I’d at least get the ball rolling on a somewhat sane, MIT licensed, alternative. Either that or just have some fun with it until someone would point me at the obvious alternative solution, which I had overlooked in my earlier search.

Project

In its initial shape, the library just lets you construct a layered network, randomize its weigths, train it with a straight forward implementation of back-propagation with adjustable learning rate and momentum, and of-course run it.

There is no serialisation interface yet, I’ll probably want to do a simplification pass over it, and I have a few edge case tests I’d like to run. However all of that is noted on the project TODO and shouldn’t amount to all that much work – in case you fancy taking a stab at it.

I did set up a little Unity project for testing though (the library itself does not depend on anything in Unity). It has a few debug views, a test scenario of the XOR case, and a curve visualisation of training error. Look, I uploaded several pretty pictures:

Access

Feel like giving it a go? As mentioned, the license is MIT, so you can really do whatever with it. However should you want to contribute, pull requests are most welcome. I don’t know how much time I can spare on this next to contracts and Behave, but at least it was a fun thing to work-on-while-not-working.

Whatever the case, this is where you can find the repositories:

Unity Protocol Buffers
Behave 2.7
Learn
Behave 2.6
Trusted Gear
Mad Mash Versioning
Behave 2.5
Behave 2.4
Co-very-routine
Construct
The Engine Wars: Numbers
GDC 14: The Quest For Fun
Moving in Unity
Behave 2.3
Unity and .net assemblies
Behave 2.2
ReView
Behave 2.1
Behave 2.0
Unity Hacks: Dual sticks
Unity Hacks: Cameras
Unity Hacks: Touch gestures
OnRenderTextureGUI
Unite 13 video "Unity Hacks" available
The implicit local network interface
Talks and progress
Five years of Unity expertise looking for contracts
Automagic Unity Android Java gadget OF DOOM!
Invading Planet from your couch
Mountain Lion and laggy bluetooth and duct-tape
Unite 12 video and new videos section available
Asia Bootcamp videos now available
Path is now MIT licensed
Behave 1.4 released
So I've been a bit busy lately
Behave 1.3 released
IGDA Unity SIG slides
Second Unity IGDA SIG this evening: Scene construction and AI
First IGDA Unity SIG this evening
Alternative licensing available
Pathfinding in two lines
Path 2 released
Assembling and assimilating
Path 2 intro screencast
Path 2 beta release for GGJ
AIgameDev master class video now online
Expanding beta
Behave AIgameDev master class public stream
Behave master class on open AIgameDev stream tomorrow
Interview with AIGameDev
New video: From tree to code
Issue tracking on github Behave release project
IT University Copenhagen Unity course completed
IT University Copenhagen Unity course files Thursday
CPH IT University Unity course files
Behave 1.2 released
Video: Behave - starting from scratch
Behave runtime documentation updated
Behave 1.1 released
FAFF cleanup: Sketch
Building a menu of delegates and enums
Pick me! Pick me!
Optimising coroutine yielding in C#
Downloading the hydra
New license of Path: GPL
CopyInspector
Magnetic
GUI drag-drop
Logging an entire GameObject
I bet you can't type an A!
Where did that component go?
UnitySteer
New and improved: Behave 1.0 released
Behave 0.3b and unity 2.5
Behave 0.3b hotfix
Path tutorial video available
Path 1.0 launched!
Continued community tutorials
Community tutorial
New tutorial
First tutorial available
Behave 0.3b
unite '08 open-mic session
Behave 0.2b
Behave 0.1b
Behave pre-release
Path beta 0.3b
Path beta 0.2b
Path beta 0.1b
Path pre-release