Predicting Machine-Learned Model Performance from the Parameter Values of the Model

    公开(公告)号:US20210256422A1

    公开(公告)日:2021-08-19

    申请号:US17177362

    申请日:2021-02-17

    Applicant: Google LLC

    Abstract: Provided are systems and methods for predicting machine learning model performance from the model parameter values, including for use in making improved decisions with regard to early stopping of training procedures. As one example, the present disclosure discusses the prediction of the accuracy (e.g., relative to a defined task and testing dataset such as a computer vision task) of trained neural networks (e.g., convolutional neural networks (CNNs)), using only the parameter values (e.g., the values of the network's weights) as inputs. As such, one example aspect of the present disclosure is directed to computing systems that include and use a machine-learned performance prediction model that has been trained to predict performance values of machine-learned models based on their parameter values (e.g., weight values and/or hyperparameter values).

Patent Agency Ranking