EDeN Update: Memory patches and speed improvements
Tests continue on the framework, which have lead to:
- Memory leak fixes.
- Various speed improvements.
- Internal fallback to protect against failure from hyper parameter options.
- Much faster and optomised randomisation utility with
- Clearer display of Functome data (The Entities ‘DNA’ of sorts)
EDeN Update: Unity volumetric connectome rendering
Significant enhancements to the backend dlls, rendering methods, and other interfaces have now allowed for the following:
- Jeffbot – Is now created by the user from the python interface client side (Or any other asset via the ‘TraniningMetaData settings)
- Neuron renderer: Rendering 10,000 neurons, each with up to 20,000 Axons/Dendrites, this will improve drastically once again given compute shader processing!
That’s up to 134,217,728 neurons rendered on the active entity!-Special thanks to Joel Rowney from Mjolnir software in his shader mastery!
Update: EDeN Unity engine rendering updates
Work progresses well in developing an entity training environment.
Included in the follow GIF, we see:
- Jeffbot – a representation of test entities where input and output neural probes are attached
- Training environment which spawns different challenges and all essential stimulus, either in the form of food or direct neural inputs
- Neuron renderer: rendering a few hundred neurons just starting to grow from initial conditions.
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!
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.
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.