Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression

Abstract

For cases in which a machine learning model needs to be adapted to a new task, various approaches have been developed, including model-agnostic meta-learning (MAML) and transfer learning. In this paper, we investigate how the differences in the data distributions between the old tasks and the new target task impact performance in regression problems. By performing experiments, we discover that these differences greatly affect the relative performance of different adaptation methods. Based on this observation, we develop ensemble schemes combining multiple adaptation methods that can handle a wide range of data distribution differences between the old and new tasks, thus offering more stable performance for a wide range of tasks. For evaluation, we consider three regression problems of sinusoidal fitting, virtual reality motion prediction, and temperature forecasting. The evaluation results demonstrate that the proposed ensemble schemes achieve the best performance among the considered methods in most cases.

Method for Evaluating Degradation of Battery Capacity Based on Partial Charging Segments for Multi-Type Batteries

“…After the update, the model obtains the corresponding loss through the query set. Finally, the loss sum of all tasks is counted to provide gradient information for the update of the initial parameters of the model [52].…”

Velocity- and Error-Aware Switching of Motion Prediction Models for Cloud Virtual Reality

“…In [14] and [15], the authors developed a prediction algorithm using an MLP and a framework for streaming 360-degree videos based on viewer motion prediction. The authors of [16] applied model-agnostic meta-learning to a one-dimensional CNN for predicting the head orientation of a new user. The authors of [20] proposed offline learning algorithms for head orientation prediction using linear regression (LR), MLP, and RNN models based on LSTM and GRU architectures.…”

“…Both show acceptable prediction results for short prediction intervals but fail for long intervals because the assumptions become unaligned with reality. Multiple machine learning (ML)-based prediction solutions have also been proposed based on a linear regression model [13], multilayer perceptrons (MLPs) [14], [15], convolutional neural networks (CNNs) [16], recurrent neural networks (RNNs) [17]- [19], long short-term memory (LSTM) [20], [21], and gated recurrent units (GRUs) [20], [22], which learn the correlations between past head pose data and the future head pose. Another approach to motion prediction is to utilize the user's neck surface electromyographic (sEMG) data to make predictions using a trained artificial neural network, based on the fact that myoelectric signals precede exertion [23], [24].…”

Clinical Application of an Artificial Intelligence System for Diagnosing Thyroid Disease Based on a Computer Neural Network Deep Learning Model

“…This mode can reduce the problem to its simplest form and automatically construct a complex model. For example, some researchers use shift learning models trained using digital camera images 6 (eg, YOLO, ImageNet); however, medical images are different from ordinary digital camera images and image formation principles, hence creating an original model of shift learning using medical images will be optimal. Due to the differences in various types of medical images (eg, CT, MRI), target sites and imaging methods, it is necessary to develop shift learning models for each case in this stage.…”