Method and apparatus for continuous learning using asymmetric structures
AssigneeINFINIQ Co., Ltd.
InventorsMin Jae JUNG, Joo Hee KIM, Seung Jin OH, Seung Taek KIM, Kyung Shil KANG
Life of this patent
Estimating the term…
Loading patent…
AssigneeINFINIQ Co., Ltd.
InventorsMin Jae JUNG, Joo Hee KIM, Seung Jin OH, Seung Taek KIM, Kyung Shil KANG
Estimating the term…
The present invention aims to minimize catastrophic forgetting that occurs during the continual learning process of a large language model (LLM), and to improve the model's performance by efficiently acquiring new knowledge. A memory of a continual learning apparatus using an asymmetric structure according to one embodiment of the present invention may store datasets used for continual learning, model parameters, a router, and adapters. At least one processor may be configured to perform continual learning using a neural network model comprising a shallow layer and a deep layer; to add a new adapter corresponding to new learning to the deep layer whenever new data is learned; and to distribute input text to at least one of the shallow layer, the deep layer, and the adapter via a router provided between the shallow layer and the deep layer.
A continual learning apparatus using an asymmetric structure, the continual learning apparatus comprising:
A method of a continual learning using an asymmetric structure, the method comprising:
Dependencies are inferred from the claim text.