Microsoft technology licensing, llc (20240296309). INCORPORATING STRUCTURED KNOWLEDGE IN NEURAL NETWORKS simplified abstract

From WikiPatents
Jump to navigation Jump to search

INCORPORATING STRUCTURED KNOWLEDGE IN NEURAL NETWORKS

Organization Name

microsoft technology licensing, llc

Inventor(s)

Bhaskar Mitra of Montreal (CA)

Yordan Kirilov Zaykov of Cambridge (GB)

John Michael Winn of Redmond (GB)

James John Hensman of Redmond (GB)

INCORPORATING STRUCTURED KNOWLEDGE IN NEURAL NETWORKS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240296309 titled 'INCORPORATING STRUCTURED KNOWLEDGE IN NEURAL NETWORKS

    • Simplified Explanation:**

The patent application describes a method for structured knowledge modeling and incorporating learned knowledge in neural networks. The knowledge is stored in a knowledge base in a structured and human-interpretable manner, allowing neural networks to read from and write to it using structured queries.

    • Key Features and Innovation:**
  • Knowledge is encoded in a structured knowledge base that is human-interpretable, verifiable, and editable.
  • Another neural network can interact with the knowledge base through structured queries.
  • The knowledge base has an interpretable property name-value structure, allowing for structured queries to be formulated by a neural model.
  • The knowledge base supports gradient-based training or updates, enabling knowledge to be inferred from a training set using machine learning methods.
    • Potential Applications:**

This technology can be applied in various fields such as natural language processing, information retrieval, and knowledge representation systems.

    • Problems Solved:**

This technology addresses the challenges of encoding and utilizing structured knowledge in neural networks in a human-interpretable and verifiable manner.

    • Benefits:**
  • Improved interpretability and verifiability of knowledge in neural networks.
  • Enhanced ability to incorporate learned knowledge into neural models.
  • Facilitates structured queries and interactions with the knowledge base.
    • Commercial Applications:**

Potential commercial applications include developing intelligent chatbots, recommendation systems, and knowledge management tools for businesses.

    • Questions about Structured Knowledge Modeling:**

1. How does this technology improve the interpretability of knowledge in neural networks? 2. What are the potential real-world applications of incorporating learned knowledge in neural models?

    • Frequently Updated Research:**

Stay updated on advancements in structured knowledge modeling and neural network integration for improved knowledge representation and utilization.


Original Abstract Submitted

an approach to structured knowledge modeling and the incorporation of learned knowledge in neural networks is disclosed. knowledge is encoded in a knowledge base (kb) in a manner that is explicit and structured, such that it is human-interpretable, verifiable, and editable. another neural network is able to read from and/or write to the knowledge model based on structured queries. the knowledge model has an interpretable property name-value structure, represented using property name embedding vectors and property value embedding vectors, such that an interpretable, structured query on the knowledge base may be formulated by a neural model in terms of tensor operations. the knowledge base admits gradient-based training or updates (of the knowledge base itself and/or a neural network(s) supported by the knowledge base), allowing knowledge or knowledge representations to be inferred from a training set using machine learning training methods.

Retrieved from "http://wikipatents.org/index.php?title=Microsoft_technology_licensing,_llc_(20240296309)._INCORPORATING_STRUCTURED_KNOWLEDGE_IN_NEURAL_NETWORKS_simplified_abstract&oldid=224682"