KR-20260064927-A - CONTINUOUS LEARNING METHOD AND CONTINUOUS LEARNING DEVICE BASED ON SELF-PACED MECHANISM

Abstract

The present invention relates to a self-paced continuous learning device comprising: a training data construction unit that calculates a loss value for each sample of a new task and, based on the calculated loss value, measures the complexity of the samples and constructs training data by self-paced sampling in order from easy samples with relatively low complexity to difficult samples with relatively high complexity; a forgetting occurrence confirmation unit that, during the training process of the new task, checks whether forgetting has occurred for each sample of a previously trained previous task and stores the forgotten sample in a replay memory; and a learning unit that continuously trains a pre-prepared model based on the training data of the new task and the samples of the previous task stored in the replay memory.

Inventors

• 권혁윤
• 김민선

Assignees

• 서울과학기술대학교 산학협력단

Dates

Publication Date

20260508

Application Date

20241030

Claims (5)

1. A training data construction unit that calculates a loss value for each sample of a new task, measures the complexity of the samples based on the calculated loss value, and constructs training data by self-paced sampling in order from easy samples with relatively low complexity to difficult samples with relatively high complexity; A forgetting occurrence checking unit that, during the training process of the above-mentioned new task, checks whether forgetting has occurred for each of the previously trained samples of the previous task and stores the forgotten samples in a replay memory; and A self-regulating continuous learning device comprising: a learning unit that continuously trains a pre-prepared model based on the training data of the new task and samples of the previous task stored in the iteration memory.
2. In paragraph 1, The above-mentioned learning data construction unit is, A self-regulating continuous learning device that measures the complexity by comparing the loss value for each sample of the new task with a predefined dynamic learning threshold, determines a sample with a loss value smaller than the dynamic learning threshold as an easy sample, and determines a difficult sample by increasing the dynamic learning threshold.
3. In paragraph 1, The above-mentioned forgetfulness occurrence confirmation unit is, A self-regulating continuous learning device that checks for each of the samples of the previous task whether forgetting has occurred during the entire epoch of the learning process of the new task, and determines the sample in which the prediction accuracy of the model switches from True to False as the sample in which forgetting has occurred.
4. In paragraph 3, The above-mentioned forgetfulness occurrence confirmation unit is, A self-regulating continuous learning device that inputs training data of the new task and samples of the previous task stored in the iteration memory into the model in which the continuous learning is completed to predict class labels, and updates the iteration memory by checking whether forgetting has occurred according to the prediction accuracy of the model.
5. A step of constructing training data by calculating a loss value for each sample of a new task, measuring the complexity of the samples based on the calculated loss value, and self-paced sampling in order from easy samples with relatively low complexity to difficult samples with relatively high complexity; During the training process of the new task, a step of checking whether forgetting has occurred for each of the previously trained samples of the previous task, and storing the forgotten samples in a replay memory; and A self-regulated continuous learning method comprising the step of continuously training a pre-prepared model based on the training data of the new task and samples of the previous task stored in the iterative memory.

Description

Continuous Learning Method and Continuous Learning Device Based on Self-Paced Mechanism The present invention relates to a continuous learning method and a continuous learning device based on a self-paced mechanism. Continuous learning algorithms are designed to solve non-independent and non-identically distributed (Non-IID) scenarios. Unlike conventional deep learning algorithms that assume data is IID, continuous learning approaches must consider that data distributions can change over time. In such cases, models trained to minimize empirical risk are vulnerable to catastrophic forgetting, where they lose previously acquired knowledge and adapt to new data. Furthermore, artificial intelligence models must be regularly updated to respond to real-time changing data distributions, during which the models are retrained using all accumulated data. However, this retraining is unsuitable for real-time data processing due to the exponential increase in computational costs and training time, and places a significant burden on system resources as more memory is required to store and process continuously growing datasets. Meanwhile, self-regulated learning is a method in which an artificial intelligence model adjusts the difficulty and order of the data it learns during the learning process. Similar to the human learning process, it starts with easy tasks and gradually learns more difficult tasks as learning progresses. Thus, since self-regulated learning learns gradually starting from easy samples, the AI model can proceed with learning quickly without feeling burdened by complex problems from the beginning, and can improve learning performance by gradually learning difficult samples. Therefore, research is needed on ways to apply these principles of self-regulated learning to continuous learning problems. FIG. 1 is a diagram illustrating the internal blocks of a self-regulated continuous learning device according to an embodiment of the present invention, FIG. 2 is a diagram illustrating the detailed operation of a self-regulated continuous learning device according to an embodiment of the present invention. FIG. 3 is a diagram for explaining the operation of the forgetting occurrence verification unit of FIG. 1 verifying whether forgetting has occurred. FIG. 4 is a diagram for explaining the operation of the forgetting occurrence confirmation unit of FIG. 1 updating the repetitive memory. And, FIG. 5 is a flowchart showing the continuous learning operation of a self-regulating continuous learning device according to an embodiment of the present invention. The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in relation to one embodiment. It should also be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the invention is limited only by the appended claims, including all equivalents to those claimed therein, provided appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects. The components according to the present invention are defined by functional distinction rather than physical distinction, and can be defined by the functions each performs. Each component may be implemented as hardware or as program code and processing units that perform each function, and the functions of two or more components may be included and implemented in a single component. Therefore, it should be noted that the names assigned to the components in the following embodiments are not intended to physically distinguish each component but are assigned to imply the representative function performed by each component, and that the technical concept of the present invention is not limited by the names of the components. Preferred embodiments of the present invention will be described in more detail below with reference to the drawings. FIG. 1 is a diagram illustrating the internal blocks of a self-regulated continuous learning device according to an embodiment of the present invention, FIG. 2 is a diagram for explaining the detailed operation of a self-regulated continuous learning device according to an embodiment of the present invention, FIG. 3 is a diagram for explaining the operation of the forgetting occurrence confirmation uni