macrovsa
Implements a macroscopic algorithmic ersatz of VSA some operations
This only an alpha version, better contact us to discuss, what it is and how to use it :)
The usual Vector Symbolic Architecture are implemented at microscopic using, e.g., the Neural Engineering Framework allowing a microscopic simulation of the neuronal processes, at the spiking neural network level. At a higher scale, when implemented using Semantic Pointer Architecture, based on linear algebra and permutation operations, thus at a mesoscopic scale, it allows to perform the same operations, but without explicitizing the neural state value and evolution.
A step further, at a higher macroscopic scale, we could directly consider the previous operations predicting the result of the different algebraic operations without explicitly calculating on vector components. This could be called an ``algorithmic ersatz'', and this is what is implemented here.
Please refer to the draft in preparation here for further explanations.
Package repository
- Package files: https://gitlab.inria.fr/line/aide-group/macrovsa
- Package documentation: https://line.gitlabpages.inria.fr/aide-group/macrovsa
- Source files: https://gitlab.inria.fr/line/aide-group/macrovsa/-/tree/master/src
- Saved on softwareherirage.org
- Version
0.1.1 - License
CECILL-C
Installation
User simple installation
npm install git+https://gitlab.inria.fr/line/aide-group/macrovsa.git
Co-developper installation
- See the related documentation
Please refer to the installation guide for installation.
Usage
npm script usage
npm install --quiet : installs all package dependencies and sources.
npm run build: builds the different compiled, documentation and test files.
npm test : runs functional and non-regression tests.
npm run clean: cleans installation files.
Dependencies
- aidesys: Basic system C/C++ interface routines to ease multi-language middleware integration
- wjson: Implements a JavaScript JSON weak-syntax reader and writer