18481607. MACHINE LEARNING MODEL GENERATION APPARATUS, MACHINE LEARNING MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM simplified abstract (NEC Corporation)

From WikiPatents
Jump to navigation Jump to search

MACHINE LEARNING MODEL GENERATION APPARATUS, MACHINE LEARNING MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

Organization Name

NEC Corporation

Inventor(s)

Yuki Kosaka of Tokyo (JP)

Shinto Eguchi of Tokyo (JP)

MACHINE LEARNING MODEL GENERATION APPARATUS, MACHINE LEARNING MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM - A simplified explanation of the abstract

This abstract first appeared for US patent application 18481607 titled 'MACHINE LEARNING MODEL GENERATION APPARATUS, MACHINE LEARNING MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

Simplified Explanation

The patent application describes a machine learning model generation apparatus that includes a movement unit and a generation unit.

  • The movement unit performs movement processing by transferring a sample from a target sample group to a source sample group if the output error of a (t+1)-th order machine learning model with respect to observation data at time t+1 exceeds a predetermined amount.
  • The generation unit generates a plurality of weak learners using observation data from samples in the target sample group and the source sample group after the movement processing. It then generates a t-th order machine learning model based on these weak learners, evaluating the classification error for each weak learner using observation data at time t from the sample in the target sample group after the movement processing.

Potential applications of this technology:

  • Machine learning model generation for various tasks such as image recognition, natural language processing, and predictive analytics.
  • Adaptive machine learning models that can adjust and improve their performance over time.

Problems solved by this technology:

  • Overcoming the limitations of a single machine learning model by generating a higher-order model that combines multiple weak learners.
  • Addressing the issue of output errors exceeding a predetermined threshold by transferring samples between target and source sample groups.

Benefits of this technology:

  • Improved accuracy and performance of machine learning models by generating higher-order models.
  • Adaptability to changing data patterns and improving model performance over time.
  • Efficient utilization of observation data by transferring samples between target and source sample groups.


Original Abstract Submitted

A machine learning model generation apparatus includes: a movement unit that performs movement processing of moving a sample, having an output error of a (t+1)-th order machine learning model with respect to observation data at time t+1 being larger than a predetermined amount, from the target sample group to a source sample group; and a generation unit that generates a plurality of weak learners by using at least observation data of a sample included in the target sample group after the movement processing and a sample included in the source sample group after the movement processing, and generates a t-th order machine learning model, based on at least each of the plurality of weak learners, and a classification error being evaluated, for each of the plurality of weak learners, by using observation data at time t of the sample included in the target sample group after the movement processing.