[2Win5] Poster session 2

[2Win5-03] Investigation of Weight Characteristics in Convolutional Neural Networks Based on Layer Depth

〇Sora Togawa¹, Kenya Jin'no¹ (1.Graduate School of Tokyo City University)

Keywords:Convolutional Neural Network, Model Merge, Image Recognition, Artificial Intelligence, Deep Learning

The purpose of this study was to clarify the characteristics of the weights in each layer of a convolutional neural network, focusing on the relationship between the weights and the depth of the layers. We performed weight replacement and linear combination experiments using CNNs with the same structure trained on different datasets. We also analyzed the effect of retraining the Batch Normalization layer. Experimental results showed that the weights of the shallow layer are highly dependent on the dataset, and their characteristics appear as differences in the output distribution, which can be handled by appropriate normalization. On the other hand, the weights of the deeper layers showed a linear similarity between the layers and a relatively small dependence on the dataset.