You are hereOverview / Projects

Projects


Open Mind Common Sense

ConceptNet A large-scale semantic network (over 250,000 links) relating a wide variety of ordinary objects, events, places, actions, and goals by 20 different link types.

AnalogySpace AnalogySpace is a way of representing a knowledge base of common sense in a multidimensional vector space. It can be used to infer new common sense knowledge, organize ideas into ad-hoc categories, detect topics in text, correlate knowledge between different languages or data sources, and compare concepts on arbitrary scales that can be generated on the fly.

PerspectiveSpace PerspectiveSpace is an analysis of person-to-person interactions that explores the similarities and differences in what people believe by discovering descriptive axes on which people can be arranged.

Divisi We have developed technology that enables easy analysis of semantic data, blended in various ways with common sense world knowledge. Divisi is a open source software package to enable work with AnalogySpace, PerspectiveSpace and using 2nd order and higher SVD in Python.

GlobalMind GlobalMind is a network of multilingual/multicultural common sense databases.

The Emotion Machine Rather than seeking a best way to organize agents, this architecture supports multiple 'ways to think', each a different architectural configuration of agents. Each agent may use a different way to represent and reason with knowledge, and there are special 'panalogy' mechanisms that link agents that represent similar ideas in different ways.

Archive

Roboverse Architecture Roboverse was a tool to research about cognitive architectures, an 'artificial life' scenario where two or three simulated people in a virtual world work together to build complex structures from simple objects like sticks, balls, and blocks.

LifeNet A large-scale probabilistic graphical model (over 400,000 links) that represents common sense in the form of temporal and atemporal connections between first person probabilistic propositions. The underlying representation is based on Dynamic Markov Networks.

StoryNet A database of story scripts. One of the representations we use are natural language story templates composed from Wendy Lehnert's plot units.