DSBA Lab Seminar with cs231n @Stanford

Convolutional Neural Networks for Visual Recognition

Original course homepage: http://cs231n.stanford.edu/

YouTube Playlist

참여 인원: 지도교수 강필성, 박사과정 김준홍, 김창엽, 통합과정 김형석, 김동화, 박민식, 서승완, 석사과정 김보섭, 김해동, 조수현, 서덕성, 박재선, 이기창, 모경현, 정재윤, 장명준

Schedules

1. Introduction to Computer Vision, historical context (Mo, KH)
   • Slide with presentation
2. Image classification, k-NN, and Linear classification I (Seo, DS)
   • Slide with presentation
3. Linear classification II Higher-level representations, image features Optimization, stochastic gradient descent (Kim, CY)
   • Slide with presentation
4. Backpropagation Introduction to neural networks (Kim, HD)
   • Slide with presentation
5. Training Neural Networks Part 1 (Kim, JH)
   • Slide with presentation
6. Training Neural Networks Part 2 (Kim, JH)
   • Slide with presentation
7. Convolutional Neural Networks (Kim, BS)
   • Slide with presentation
8. ConvNets for spatial localization Object detection (Park, MS)
   • Slide with presentation
9. Understanding and visualizing Convolutional Neural Networks Backprop into image (Kim, DH)
   • Slide with presentation
10. Recurrent Neural Networks (Lee, GC)
    • Slide with presentation
11. Training ConvNets in practice (Seo, DS)
    • Slide with presentation
12. Overview of Caffe/Torch/Theano/TensorFlow
    • Skip
13. Segmentation, Soft attention models, Spatial transformer networks (Park, JS)
    • Slide with presentation
14. ConvNets for videos Unsupervised learning (Kim, DH)
    • Slide with presentation
15. Invited Talk by Jeff Dean
    • Skip