Skip to main content

LLFO - Lifelong Learning in Flexible Ontologies

A Python package implementing lifelong learning algorithms with flexible ontological structures.

Theory

LLFO combines lifelong learning with flexible ontological structures to enable continuous knowledge acquisition and adaptation. Key concepts include:

Flexible Ontologies

  • Dynamic knowledge representation through adaptable concept hierarchies
  • Automatic restructuring of relationships between concepts
  • Probabilistic edge weights between ontological nodes

Lifelong Learning Components

  • Knowledge retention through experience replay
  • Forward transfer to new tasks
  • Backward transfer to improve previous knowledge
  • Catastrophic forgetting prevention

Learning Mechanisms

  • Ontology structure learning
  • Parameter learning within nodes
  • Relationship weight adaptation
  • Task-specific adaptation

Installation

pip install -e .

Usage

import llfo

# Example code coming soon

License

MIT

Metadata

Release files for llfo 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llfo 0.1.0
File Size Uploaded Provenance Actions
llfo-0.1.0.tar.gz 2.0 kB Without provenance Details for llfo-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llfo 0.1.0
File Interpreter ABI Platform Actions
llfo-0.1.0-py3-none-any.whl Python 3 none any Details for llfo-0.1.0-py3-none-any.whl

Total release size: 3.9 kB

Release files / llfo-0.1.0.tar.gz

Download URL llfo-0.1.0.tar.gz
Size 2.0 kB
Tags Source
SHA-256 checksum
How to use checksums
79196e6009997983f94f99475321651053af15dea43d808de7e9eb8475d65415
BLAKE2b-256 checksum
How to use checksums
c4b009e5a1eb0d86fc4c7242d988ad20272fe74b637084675ca8210cf4d0e919
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.6.1 CPython/3.10.14 Darwin/23.6.0

Release files / llfo-0.1.0-py3-none-any.whl

Download URL llfo-0.1.0-py3-none-any.whl
Size 2.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6d85e17ea0a75f1015fd5bbd50b7e8be82a1546d5787df6cc771dea3e35b1846
BLAKE2b-256 checksum
How to use checksums
2d6b627de722667597c951df18973338db5d7365fc42b885ae27e49535a59d21
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.6.1 CPython/3.10.14 Darwin/23.6.0

Security for llfo 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page