System and method using separable transfer learning-based artificial neural network

A computing system using machine learning-based artificial intelligence, the computing system comprising:

• at least one processor;
• a first artificial neural network configured to pre-train on a first phase task based on a first dataset;
• and
• a second artificial neural network configured to pre-train on a second phase task based on a second dataset,
• wherein the at least one processor selects any one of the first artificial neural network and the second artificial neural network as a target artificial neural network configured to train on a target task based on a target dataset after pre-training of the first artificial neural network and pre-training of the second artificial neural network,
• wherein when the second artificial neural network is selected as the target artificial neural network, the at least one processor transfers a parameter of a first phase layer of the first artificial neural network to a first phase of the target artificial neural network after the pre-training of the first artificial neural network,
• wherein when the first artificial neural network is selected as the target artificial neural network, the at least one processor transfers a parameter of a second phase layer of the second artificial neural network to a second phase of the target artificial neural network after the pre-training of the second artificial neural network, and
• wherein the at least one processor performs control so that the target artificial neural network performing fine-tuning training on the target task after the transfer of the parameter of the first phase layer of the first artificial neural network or the transfer of the parameter of the second phase layer of the second artificial neural network to the target artificial neural network.

An artificial neural network training method executed in a computing system including a machine learning-based artificial neural network, the artificial neural network training method comprising:

• controlling, by at least one processor in a computing system, pre-training of a first artificial neural network so that the first artificial neural network pre-trains on a first phase task based on a first dataset;
• controlling, by the at least one processor, pre-training of a second artificial neural network so that the second artificial neural network pre-trains on a second phase task based on a second dataset;
• transferring, by the at least one processor, a parameter of a first phase layer of the pre-trained first artificial neural network to a first phase layer of a target artificial neural network;
• transferring, by the at least one processor, a parameter of a second phase layer of the pre-trained second artificial neural network to a second phase layer of the target artificial neural network;
• and
• controlling, by the at least one processor, fine-tuning training of the target artificial neural network so that the target artificial neural network performs fine-tuning training on a target task based on a target dataset.