Merging machine learning & human understanding.

Capture a decision
Reason a decision
Justify a decision
Share a decision
Report a decision
Audit a decision

Symbolic Sciences is developing expert systems to capture and digitise human-held expert knowledge.

From concept mapping - to ontologies - to knowledge graphs, our aim is to build hybrid human - machine systems to enable: (i) knowledge capture and sharing within groups, (ii) joint human - machine reasoning, and (iii) decision auditing.

"Never Forget"

Balanced Human - Machine Learning

We are experimenting with ontology-driven expert knowledge models to merge human and computer reasoning. Our goal is to enable real-time sense-checking of human decision making .

To do this, our research is focused on the digital capture and mapping of the nuanced, human-led decision-making process. A key input is the encoding of both measured and perceived uncertainty.

Symbolic Sciences is a Cambridge-based micro-SME exploring new ways of capturing, auditing and sense checking human-held technical knowledge with the help of machine reasoning. [ coming soon]