Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unleashing Artificial Cognition: Integrating Multiple AI Systems

Muntasir Adnan, Buddhi Gamage, Zhiwei Xu, Damith Herath, Carlos C. N. Kuhn

TL;DR

An innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence is presented, seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations.

Abstract

In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. The introduced open-source AI system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations. Leveraging a vector database to achieve retrievable answer generation, our AI system elucidates its decision-making process, bridging the gap between raw computation and human-like understanding. Our choice of Chess as the demonstration environment underscores the versatility of our approach. Beyond Chess, our system holds promise for diverse applications, from medical diagnostics to financial forecasting. Our AI system is available at https://github.com/TheOpenSI/CoSMIC.git

Unleashing Artificial Cognition: Integrating Multiple AI Systems

TL;DR

An innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence is presented, seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations.

Abstract

In this study, we present an innovative fusion of language models and query analysis techniques to unlock cognition in artificial intelligence. The introduced open-source AI system seamlessly integrates a Chess engine with a language model, enabling it to predict moves and provide strategic explanations. Leveraging a vector database to achieve retrievable answer generation, our AI system elucidates its decision-making process, bridging the gap between raw computation and human-like understanding. Our choice of Chess as the demonstration environment underscores the versatility of our approach. Beyond Chess, our system holds promise for diverse applications, from medical diagnostics to financial forecasting. Our AI system is available at https://github.com/TheOpenSI/CoSMIC.git
Paper Structure (9 sections, 5 equations, 2 figures, 1 table)

This paper contains 9 sections, 5 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Proposed System for Demonstrating Cognitive Abilities
  4. Scoring Mechanism
  5. Experiments
  6. Evaluation on System Services
  7. Evaluation on System Cognition Capability
  8. Future Work
  9. Conclusion

Figures (2)

  • Figure 1: System Architecture and Data Flow
  • Figure 2: The chart on the left displays the normalised scores for the five cognitive qualities measured using the OpenSI-CoSMIC AI System powered with several LLMs. On the right, we evaluate the anticipation for how well these LLMs can predict the next move in a chess game compared to our OpenSI-CoSMIC AI System. LLMs are inferior in predicting the optimal next chess move.