Update: Unity engine Neuron renderer
Whilst work progresses well in preparing for the next research paper and demo where I will be demonstrating basic multi agent learning.
The final planned work today resulted in some visual updates that allowed me to sit back and think all the hard work is paying off.
I present here, a few captures from the live neuron renderer.
Unfortuntly I couldn’t find a single solution going back 15 years that provided this, what I thought was simple functionality. So as a background tasks, I have upgraded the framework to stream this data to the server every epoch or a set frequency that is user adjusable.
EDeN 2.5 (15th revision) Arxiv Update
I am pleased to announce the 15th revision of the paper is now available on Arxiv!
This includes various minor updates and a new section on Multi Agent training which I’ll be discussing in the next paper
Click here for Arxiv page and download!
Update: Embodied EDeN training platform
Tinkering continues!
6 Axis arm now mounted to the embedded training platform.
Upgrades also include:
.OLED Screen
.Integrated Speaker
.USB Mic
.IC2 Ultrasonic range sensor
In addition, work continues on an large Ardunio project that brings all of the googies together under one controllable script via the IC2 Hub.
EDeN Server comes to unity!
EDeN hooks up to Unity!
Both EDeNServer EDeNCore projects previously interfaced to a python runtime through a dll.
With an experimental DLL into the lesser known Unigine engine for the server.
Now with an asynchronous (DLL Internally managed) connection from the EDeNServer, Unity is now fully compatible to host both training and inference of your EDeN entities!
– This something ML Agent through tensor flow (https://github.com/Unity-Technologies/ml-agents) has yet to achieve!
I will producing an experimental package on the unity store in the future!
For now I simply ensure both ‘EDeNServerInterfaceDLL’ and ‘EDeNDataServerNETUnityDLL.dll’ are under a Plugins folder.
This is early days for a commercial product, but I hope to build up demonstrations for all to play with sooner rather than later.
Future Embodied EDeN training platform
In my (very rare) spare time I work to contribute to a whatsapp ‘Robo club’ group.
Here is a Four wheel drive platform powered by a Arduino hat, along with GPS, Accelerometer, Magnetometer, 16 Servo controllers and ultrasonic sensor.
Within the next few months I aim to get time to attach a robotic arm.
This will allow me build a software package that works will the EDeN Server APIs.
EDeN 2.0 (10th revision) accepted by Arxiv!
I am pleased to announce the 10th revision of the paper is now available on Arxiv!
Stay tuned for code demonstrations and training results!
Click here for Arxiv page and download!
Energy Decay Network (EDeN)
This paper and accompanying Python/C++ framework is the product of the author’s perceived problems with narrow (discrimination based) AI (Artificial Intelligence). The framework attempts to develop a genetic transfer of experience through potential structural expressions using a common regulation/exchange value (‘energy’) to create a model whereby neural architecture and all unit processes are co-dependently developed. These expressions are born from fractal definition, stochastically tuned and managed by genetic experience; successful routes are maintained through global rules: Stability of signal propagation/function over cross functional (external state, internal immediate state, and genetic bias towards selection of previous expressions). These principles are aimed towards creating a diverse and robust network, hopefully reducing the need for transfer learning and computationally expensive translations as demand on compute increases.