Application of Tensorized Neural Networks for Cloud Classification
This work addresses practical implementation issues in CNNs for domains like weather forecasting, specifically for cloud classification, but appears incremental as it builds on existing methods with modifications.
The study tackled the challenges of model size, overfitting, and computational time in convolutional neural networks (CNNs) by proposing a tensorized neural network (TNN) approach, which reduced model size and computational time while incorporating attention layers and contrastive self-supervised learning for cloud classification, with results showing changes in properties under batch size settings.
Convolutional neural networks (CNNs) have gained widespread usage across various fields such as weather forecasting, computer vision, autonomous driving, and medical image analysis due to its exceptional ability to extract spatial information, share parameters, and learn local features. However, the practical implementation and commercialization of CNNs in these domains are hindered by challenges related to model sizes, overfitting, and computational time. To address these limitations, our study proposes a groundbreaking approach that involves tensorizing the dense layers in the CNN to reduce model size and computational time. Additionally, we incorporate attention layers into the CNN and train it using Contrastive self-supervised learning to effectively classify cloud information, which is crucial for accurate weather forecasting. We elucidate the key characteristics of tensorized neural network (TNN), including the data compression rate, accuracy, and computational speed. The results indicate how TNN change their properties under the batch size setting.