Introduction to Convolutional Neural Networks

A Beginner's Guide To Understanding Convolutional Neural Networks.

Refs:
http://colah.github.io/posts/2014-07-Understanding-Convolutions/
Large-Scale Visual Recognition With Deep Learning (Marc'Aurelio Ranzato , Google Inc)
A Beginner's Guide To Understanding Convolutional Neural Networks(Adit Deshpande, CS Undergrad at UCLA '19)
Video Object Detection using Faster R-CNN(Jun 20, 2016paper from Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun)
Tensorflow Days (c1mone)
CS231n Convolutional Neural Networks for Visual Recognition

Transcript

1. Convolutional Neural Network Jia-Huei, Ren 2017/1/10
2. CNN
3. Convolution • Convolution – local receptive field • ReLU • Average Pooling • Max Pooling
4. Convolution
5. Local receptive field
6. Local receptive field
7. Local receptive field
8. Local receptive field
9. Fully Conneted Neural Net • Example: 1000x1000 image • 1M hidden units • 10^12 parameters!!!
10. Locally Connected Neural Net • Example: 1000x1000 image • 1M hidden units • Filter size: 10x10 • 100M parameters
11. Locally Connected Neural Net • Example: 1000x1000 image • 1M hidden units • Filter size: 10x10 • 100M parameters
12. Convolutional Net • Share parameters • Learn multiple filters. • Example: 1000x1000 image • 100 Filters • Filter size: 10x10 • 10K parameters
13. ReLU
14. Max pooling & Average pooling
15. Full connected layer
16. Refs • http://colah.github.io/posts/2014-07-Understanding- Convolutions/ • Large-Scale Visual Recognition With Deep Learning (Marc'Aurelio Ranzato , Google Inc) • A Beginner's Guide To Understanding Convolutional Neural Networks(Adit Deshpande, CS Undergrad at UCLA '19) • Video Object Detection using Faster R-CNN(Jun 20, 2016 paper from Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun) • Tensorflow Days (c1mone) • CS231n Convolutional Neural Networks for Visual Recognition
17. Thanks