18446313. INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING APPARATUS, METHOD FOR TRAINING INFERENCE MODEL, AND NON-TRANSITORY STORAGE MEDIUM simplified abstract (CANON KABUSHIKI KAISHA)

From WikiPatents
Jump to navigation Jump to search

INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING APPARATUS, METHOD FOR TRAINING INFERENCE MODEL, AND NON-TRANSITORY STORAGE MEDIUM

Organization Name

CANON KABUSHIKI KAISHA

Inventor(s)

KOHTARO Umezawa of Tokyo (JP)

RYUTA Ueda of Tokyo (JP)

RITSUYA Tomita of Kanagawa (JP)

INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING APPARATUS, METHOD FOR TRAINING INFERENCE MODEL, AND NON-TRANSITORY STORAGE MEDIUM - A simplified explanation of the abstract

This abstract first appeared for US patent application 18446313 titled 'INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING APPARATUS, METHOD FOR TRAINING INFERENCE MODEL, AND NON-TRANSITORY STORAGE MEDIUM

Simplified Explanation

The patent application describes an information processing system with two information processing apparatuses, each including an inference model based on a neural network and a training unit.

  • The first information processing apparatus acquires and trains a first inference model using teacher data, then transmits output information to the second information processing apparatus.
  • The second information processing apparatus acquires a second inference model, which is a common inference model similar to the first model, and trains it based on the output information from the first apparatus.

---

      1. Potential Applications
  • Machine learning systems
  • Artificial intelligence applications
  • Data analysis tools
      1. Problems Solved
  • Efficient training of inference models
  • Seamless communication between information processing apparatuses
  • Consistent performance across different neural networks
      1. Benefits
  • Improved accuracy of inference models
  • Faster training process
  • Enhanced collaboration between multiple processing units


Original Abstract Submitted

An information processing system includes first and second information processing apparatuses. The first information processing apparatus includes a first acquisition unit that acquires a first inference model based on a first neural network including an input layer, an intermediate layer group, and an output layer, a first training unit that trains the first inference model using teacher data, and a transmission unit that transmits output information based on forward propagation by the first training unit to the second information processing apparatus. The second information processing apparatus includes a second acquisition unit that acquires a second inference model based on a second neural network including an input layer, an intermediate layer group, and an output layer, wherein the second inference model is a common inference model and is similar to the first inference model, and a second training unit that trains the second inference model based on the output information.