Noeon Research
LinkedIn
Noeon Research
Architecture
Noeon Research is developing an architecture capable of robust multi-step reasoning and reliable problem solving. The architecture could be used as a core component for systems or products aimed at automated IT project completion, making new industrial designs, automated scientific reasoning, or creating custom neural networks.
Inner Alignment
(01)
Careful design of Knowledge Representation allows keeping goals in explicit form that helps the system pursue that goal reliably without deviations and examine conformity along the way.
research_photo
Interpretability
(02)
Discrete structures like partially ordered sets enriched with language and semantic data allow the operator to follow the reasoning trajectory and examine the internal logic of inference process.
research_photo
Reasoning and Data Separation
(03)
Unlike prevailing ML models, e.g. LLMs, our architecture separates reasoning and domain-specific ontology. Architecture is able to incorporate any ontology and can be used for solving a variety of problem classes.
research_photo
Interactivity
(04)
In case of lack of knowledge or contradictions, the system can detect the exact cause of the issue and extract required knowledge from the environment or ask the operator for clarification. This allows the system to work in a semi-supervised manner.
research_photo
Knowledge Representation
(05)
The traditional practice of embedding knowledge in weights, encountered in LLMs, leads to several limitations: the difficulty of locating specific knowledge, costly retraining for adjustments, and expenses associated with processing and acquisition of training data. Through the use of a meticulously designed explicit knowledge representation architecture, these drawbacks can be effectively addressed.
research_photo
Continual Learning
(06)
One major challenge with implementing continual learning in Machine Learning systems is expensive and unstable retraining. Noeon Research’s architecture handles new knowledge at the representation level, enabling the system to acquire and solidify up-to-date knowledge and remove obsolete and false information.
research_photo
Non-Agency
(07)
Non-agency is an essential property for AI safety, which Noeon Research works on separately from other architectural properties. In order to avoid potentially dangerous behaviour and make the system more amenable, we want to prevent the system from developing agency while retaining reliable goal pursuing abilities.
research_photo
Join Our Team
We are looking for specialists for full-time employment
Read more
nodes photo
© 2024 Noeon Research. All rights reserved.
Midtown Tower 18F, 9-7-1 Akasaka, Minato-ku, Tokyo, Japan
(01)
Partnership
LinkedIn