Putting the "I" Back into BI
Welcome to the Prolog in the LLM Era Holiday Season Special! Starring … pyswip … SWI-Prolog … the Semantic Web … data mesh … and … special guest star, ChatGPT! Notes: This blog is best consumed by first reading at least Part 1 of the series (preferably the first 3 parts): Prolog in the LLM Era – Part 1. This blog is really Part … Continue reading Prolog Strategy Map – Prolog in the LLM Era – Holiday Season Special
This post maps the ideas in the recent paper Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention (Munkhdalai, T., Faruqui, M., & Gopal, S. 2024) to concepts from my book, Enterprise Intelligence, including the Tuple Correlation Web (TCW), Insight Space Graph (ISG), and cubespace as a semantic layer. In business intelligence (BI) and … Continue reading The BI Counterpart to AI Infinite Context
The content discusses the significance of historical context in learning and decision-making, emphasizing the value of Prolog as a tool to understand complex logical rules over time. It explores how expert knowledge and decision-making evolve, and how modern technology can facilitate the integration of historical insights into artificial intelligence, enabling enriched decision-making today.
The blog post discusses the integration of Prolog with large language models (LLMs) and its application in machine learning (ML). It explores the relationship between Prolog and ML models like decision trees, association rules, clustering, linear regression, and logistic regression. It also provides an example of transforming decision tree rules into Prolog using Python.
This blog series explores the synergy between Prolog's deterministic rules and Large Language Models (LLMs). Part 1 and 2 set the stage and discussed using Prolog alongside LLMs and Knowledge Graphs. A practical use case demonstrates how Prolog, aided by LLMs, can make meaningful contributions to AI systems. The series hopes to reignite interest in Prolog.
Prolog, discussed in my "Prolog's Role in the LLM Era - Part 2" blog, offers transparent, clear rules for decision-making. This contrasts with the complexity of neural network models. Fusing fuzzy LLMs with Prolog's determinism creates a stable, reliable AI system. As technology advances, this partnership will optimize efficiency and reliability in decision-making systems.
The author recounts the challenges of pitching a product during the dot-com bubble burst, paralleling it with current skepticism towards AI. Despite the doubts, the book "Enterprise Intelligence" argues that AI, though not without flaws, can greatly enhance enterprise analytics. It emphasizes a balanced approach and offers practical knowledge for leveraging AI in business.
The book "Enterprise Intelligence" by Technics Publications, set to release on June 21, 2024, advocates for integrating AI with Business Intelligence to enhance enterprise performance. It emphasizes the importance of critical/creative thinking alongside AI and details a framework for Augmented Enterprise Intelligence. The book explores the merge of BI data and advanced AI to build adaptable and thriving enterprises in a rapidly evolving business landscape.
Introduction Back in 2006, I developed an ambitious idea that, though ahead of its time, now poses exciting possibilities in our data-driven era. The concept was simple yet potent: to construct a graph mapping various elements (such as database columns and parameters) used in formulas across Key Performance Indicator (KPI) statuses. The aim was to … Continue reading KPI Status Relationship Graph Revisited with LLMs
Soft Coded Logic 