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.
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.