Research Index

Exploring new foundations for computation.

Orion explores new foundations for computation, with an interest in what a model can retain, recover and use as its work continues.

A different foundation for intelligence.

Genesis explores how intelligence can be built from separate cooperating parts, and how such a model learns to coordinate on its own.

Discovering patterns. Developing understanding.

Self Driven Systematic Growth explores how a model can derive patterns from the information it encounters, apply what it discovers and develop the connections between what it has learnt.

Memory that can remain, recover and develop.

Athena explores how a model can carry memory forward, recover what it has retained and develop a clearer basis for knowing when that memory can be relied upon.

Preserving what a model carries forward.

Ouah explores how a model can retain the internal information it develops, preserve what that information allows it to do, and make it available again when needed.

Bringing memory back into a model's work.

Ariadne develops memory that remains available for later use, with faithful recovery as a foundation for continuing a model's work.

Learning relationships. Applying them to something new.

Odysseus explores how a model can learn from examples, recognise useful relationships and apply what it has learnt to information it has not encountered before.

Learning, retaining and developing through experience.

Eros explores how a model can learn from information, preserve what happens within it and develop the abilities needed for useful reasoning and research.

Bringing the abilities of a model together.

Sagas explores how memory, relationships, reasoning and checking can work together within one model, with each contributing to a coherent whole.

Sustaining observation. Continuing investigation.

Argus explores how an intelligent model can sustain its own activity, respond to what it encounters and develop the foundations for continued learning.

Developing new abilities. Preserving what has been learnt.

Icarus explores how a model can develop through new information while retaining the abilities it has already established.

Discovering relationships. Carrying understanding forward.

Eos explores how a model can recognise patterns in the information it encounters, investigate mathematical relationships and retain what it has established for further work.

Learning that changes what becomes possible next.

Our research into dynamic learning systems explores how earlier learning can shape later encounters, how useful connections can develop, and how what has been learnt can remain available for further use.