Machine Learning

Dynamic Weight Alignment for Convolutional Neural Networks

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 12 months ago.


  • arXiv
    5 pts

    Dynamic Weight Alignment for Convolutional Neural Networks

    In this paper, we propose a method of improving Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNNs convolve learnable shared weights, or filters, across the input data. The filters use a linear matching of weights to inputs using an inner product between the filter and a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to optimized input elements. This dynamic alignment is useful for time series recognition due to the complexities of temporal relations and temporal distortions. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.

    Dynamic Weight Alignment for Convolutional Neural Networks
    by Brian Kenji Iwana, Seiichi Uchida
    https://arxiv.org/pdf/1712.06530v1.pdf

You must be logged in to reply to this topic.