一天搞懂深度学习.ppt

文档介绍：This template is the internal standard courseware template of the enterprise
一天搞懂深度学习
目录 content
深度学习概述
第一= Many hidden layers
Special
structure
1-2 基本思想
……
……
……
……
……
……
……
……
y1
y2
yM
Neural Network
W1
W2
WL
b2
bL
x
a1
a2
y
y
x
b1
W1
x
+
b2
W2
+
bL
WL
+
…
b1
…
1-2 基本思想
……
……
……
……
……
……
……
……
y1
y2
yM
Output Layer
Hidden Layers
Input Layer
Feature extractor replacing feature engineering
= Multi-class Classifier
Softmax
1-2 基本思想
Neural
Network
1-2 基本思想
……
……
……
……
……
……
y1
y2
y10
Cross
Entropy
“1”
……
1
0
0
……
target
Softmax
……
Given a set of parameters
1-2 基本思想
Neural
Network
1-2 基本思想
Gradient Descent



……
……

-

gradient
1-2 基本思想
Neural Network
Good Results on Testing Data?
Good Results on Training Data?
YES
YES
NO
NO
Overfitting!
Deep Learning
1-2 基本思想
1-3 经典模型
DNN 深层神经网络
CNN 卷积神经网络
RNN 循环神经网络
GAN 生成对抗网络
………………………………..
Some patterns are much smaller than the whole image
A neuron does not have to see the whole image to discover the pattern.
“beak” detector
Connecting to small region with less parameters
1-3 经典模型-CNN
The same patterns appear in different regions.
“upper-left beak” detector
“middle beak” detector
They can use the same set of parameters.
Do almost the same thing
1-3 经典模型-CNN
Subsampling the pixels will not change the object
subsampling
bird
bird
We can subsample the pixels to make image smaller
Less parameters for the network to process the image
1-3 经典模型-CNN
Fully Connected Feedforward network
cat dog ……
Convolution
Max Pooling
Convolution
Max Pooling
Flatten
Can repeat many times
1-3 经典模型-