Model training method and device, electronic equipment and storage medium

Abstract

The invention discloses a model training method and device, electronic equipment and a storage medium, and relates to the technical field of deep learning. According to the specific implementation scheme, derivative models are generated according to an obtained meta-model set, the multiple derivative models are added into the meta-model set as meta-models, and the number of models in the meta-model set is increased for subsequent meta-training on the meta-model set; and then, the meta-models in the meta-model set are screened according to the performance parameters of the trained meta-models so as to obtain the meta-models with good performance for adaptive training of a target task. According to the model training method and device, the electronic equipment and the storage medium, the manner of carrying out screening after enriching the meta-models is adopted, so that the performance of the screened and reserved meta-models is improved, an adaptive training result does not need to bereversely transmitted to a meta-training process, a better training result can also be achieved, and the training efficiency is effectively improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, specifically to the technical field of deep learning, especially to a model training method, device, electronic equipment and storage medium. Background technique [0002] At present, how to adapt robots to a wide range of tasks is one of the important factors to further improve artificial intelligence. Due to traditional machine learning or reinforcement learning techniques, robots can only be trained for a specific task. For example, it is possible to make a robot walk with two legs with certain geometric parameters and with specific motors. But once the parameters of the legs, such as leg length, are switched, the model cannot continue to be used and needs to be retrained. This severely limits the application capabilities of AI today. [0003] In related technologies, the application ability of artificial intelligence is improved through the combination of "meta-lea...

AI Technical Summary

Problems solved by technology

But once the parameters of the legs are switched, such as the length of the legs, the model cannot continue to be used and needs to be retrained

This severely limits the application capabilities of AI today

[0003] In related technologies, the application ability of artificial intelligence is improved through the combination of "meta-learning" and "adaptive learning". When the task performs gradient backhaul, when the adaptation process is long, the meta-model training has a large burden, which makes the training efficiency drop rapidly

Images