- R0
- Day 2, 14:05‑14:35
- Chinese talk w. English slides
- Graphics
- Novice
Flying over Taipei with Van Gogh and His Friends
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。
Talk Detail
* 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!
Slides Link
Speaker Information
Peter Yeh
A student in National Taiwan University. I am interested in Deep Learning and its application.