Robonaissance
Research project
Learning from Experience through Adaptive Plasticity
Building AI systems that learn better from experience.
The missing layer
Between remembering and retraining
Most current AI memory systems focus on retaining and retrieving information. Most learning systems rely on offline training or opaque weight updates. LEAP studies the missing layer between them: how ongoing experience should become durable, inspectable, revisable knowledge and better future behavior.
Memory systems
Retain and retrieve information.
LEAP
Ongoing experience becomes durable, inspectable, revisable knowledge and better future behavior.
Learning systems
Offline training or opaque weight updates.
Definition
When has a system learned?
When experience changes what it understands, predicts, or does in the future, while it
- Ipreserves useful prior knowledge,
- IIrespects scope and authority,
- IIIand remains able to recover from mistaken learning.
The loop
A continuous loop
LEAP studies how each turn of this loop turns what happened into what the system knows and does next.
- Experience
- Learning Proposal
- Adaptive Plasticity
- Consolidation
- Action
- Outcome
- Revision
- and back to Experience
Memory is how experience becomes learning.
Powered by LEAP
The first application: Pompom
Pompom is a LEAP-powered Markdown notebook.
It remembers what matters, learns from your experiences, and connects what you know, helping you think, learn, and make better decisions.