BAI-OptiMa project

Major active project

BAI-OptiMa (BenAI Optimal individualised decision Making foundational framework and algorithms) project is based on future intelligence envisaged by BenAI, which was originated from Clinical Decision Support System and is being generalised

Major Innovations

AI Theory

Inductive Learning: a fourth learning method after Supervised Learning, Unsupervised Learning, Reinforcement Learning

Maths

Decision logic (D-logic) extends traditional classification based decision-making

Architecture

  • The GID model: prediction module + rules module + trainable process module + rule-enforcement-module
  • Enabling small dataset training by introducing SDAaa generalisation and domain knowledge

Algorithms

  • The logic-MCUR algorithm: implementation of D-logic
  • The DoNDe algorithm: model-agnostic AI explainability
  • The DEENa algorithm: extract domain data/rules from natural language
  • The SiR algorithm: find similar cases

Technical documentation

Around 10 algorithms

BAI-OptiMa.pdf

滚动至顶部