Flying over Taipei with Van Gogh and His Friends

  • R0
  • 第 2 天，14:05‑14:35
  • 中文演講/英文投影片
  • 圖像處理
  • 入門

想像我們飛過臺北的天空，欣賞梵谷和大師們筆下的臺北！

Deep Learning 讓這件事變得可能！
這次短講，我們想和大家分享深度學習如何讓電腦學會大師的筆觸和風格(Convolutional Neural Networks, CNN)。以及我們如何結合在地特色實作的成果。

關於背景知識，並不設限，我們會從簡單的概念開始談起，如果有基本的數學認識尤佳。

演講詳細內容

* Some Reading Materials: 1.A Quick Introduction to Neural Networks
(https://ujjwalkarn.me/2016/08/09/quick-intro-neural-networks/ ) 2.An Intuitive Explanation of Convolutional Neural Networks
(https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/) 3.A Neural Algorithm of Artistic Style
(https://arxiv.org/pdf/1508.06576v2.pdf) 4.Perceptual Losses for Real-Time Style Transfer and Super-Resolution
(https://arxiv.org/abs/1603.08155) 5.Neural Style Transfer: A Review
(https://arxiv.org/pdf/1705.04058.pdf) * Our Gitlab: https://gitlab.com/DeepArtPlus/TrainingModel-Release We provide some fast neural style model here. If you like art style transfer, take a try!

投影片連結

講者介紹

Peter Yeh

A student in National Taiwan University. I am interested in Deep Learning and its application.