Lecture 10: Recurrent Neural Networks - Stanford University
Lecture 10: Recurrent Neural Networks
Fei-Fei Li & Justin Johnson & Serena Yeung
Lecture 10 - 1 May 4, 2017
Administrative
A1 grades will go out soon
A2 is due today (11:59pm)
Midterm is in-class on Tuesday! We will send out details on where to go soon
Fei-Fei Li & Justin Johnson & Serena Yeung
Lecture 10 - 2 May 4, 2017
Extra Credit: Train Game
More details on Piazza by early next week
Fei-Fei Li & Justin Johnson & Serena Yeung
Lecture 10 - 3 May 4, 2017
Last Time: CNN Architectures
AlexNet
Fei-Fei Li & Justin Johnson & Serena Yeung
Figure copyright Kaiming He, 2016. Reproduced with permission.
Lecture 10 - 4 May 4, 2017
Last Time: CNN Architectures
Softmax FC 1000 FC 4096 FC 4096
Pool 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512
Pool 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512
Pool 3x3 conv, 256 3x3 conv, 256
Pool 3x3 conv, 128 3x3 conv, 128
Pool 3x3 conv, 64 3x3 conv, 64
Input
VGG16
Softmax FC 1000 FC 4096 FC 4096
Pool 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512
Pool 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512 3x3 conv, 512
Pool 3x3 conv, 256 3x3 conv, 256
Pool 3x3 conv, 128 3x3 conv, 128
Pool 3x3 conv, 64 3x3 conv, 64
Input
VGG19
GoogLeNet
Fei-Fei Li & Justin Johnson & Serena Yeung
Figure copyright Kaiming He, 2016. Reproduced with permission.
Lecture 10 - 5 May 4, 2017
Last Time: CNN Architectures
relu F(x) + x
conv
F(x)
relu
conv
X identity
X Residual block
Softmax FC 1000
Pool
3x3 conv, 64 3x3 conv, 64
3x3 conv, 64 3x3 conv, 64
3x3 conv, 64 3x3 conv, 64
...
3x3 conv, 128 3x3 conv, 128
3x3 conv, 128 3x3 conv, 128
3x3 conv, 128 3x3 conv, 128 / 2
3x3 conv, 64 3x3 conv, 64
3x3 conv, 64 3x3 conv, 64
3x3 conv, 64 3x3 conv, 64
Pool 7x7 conv, 64 / 2
Input
Fei-Fei Li & Justin Johnson & Serena Yeung
Figure copyright Kaiming He, 2016. Reproduced with permission.
Lecture 10 - 6 May 4, 2017
DenseNet
1x1 conv, 64 Concat
1x1 conv, 64 Concat Conv Concat Conv Input
Dense Block
Softmax FC Pool
Dense Block 3 Conv Pool Conv
Dense Block 2 Conv Pool Conv
Dense Block 1 Conv Input
FractalNet
Figures copyright Larsson et al., 2017. Reproduced with permission.
Fei-Fei Li & Justin Johnson & Serena Yeung
Lecture 10 - 7 May 4, 2017
Last Time: CNN Architectures
Fei-Fei Li & Justin Johnson & Serena Yeung
Lecture 10 - 8 May 4, 2017
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- cnn 10 student news guided worksheet
- audience report on cnn mit media lab
- certification examination application
- for release monday november 19 at 10 am
- cnn t r t r nh p ima p ll
- hierarchical transfer convolutional neural networks for
- com
- lecture 10 recurrent neural networks stanford university
- libra r cnn towards balanced learning for object detection
- lecture 9 cnn architectures stanford university
Related searches
- types of recurrent neural network
- recurrent neural network architecture
- recurrent neural network explained
- recurrent neural net
- recurrent neural network tutorial
- recurrent neural network example
- training recurrent neural network
- recurrent neural network definition
- what is recurrent neural network
- recurrent neural network wiki
- recurrent neural network code
- recurrent neural network application