Deep Learning
Alvin Chan
with
CNN
Resources
Dataset
- Image
- Text
- Graphs
- etc
Model
- With layers of 'neurons'
- Dense layer
- Convolutional layer
- Recurrent layer
- etc
Optimizer
- Adjust learned 'knowledge'
- Examples
- SGD
- ADAM
A neuron
input_1
input_2
input_3
output
param_1
param_2
param_3
+
+
=
output
input_1 * param_1 input_2 * param_2 input_3 * param_3
'Rectangle' neuron
length
breadth
brightness
perimeter
x0
x2
x2
length
breadth
Deep learning
input_1
input_2
input_3
output
Relu Activation Function
- Dense Layer
- Convolutional Layer
- Recurrent Layer
- Many more..
of neural layer
Types
Dense layers
Dense Layer 1
Dense Layer 2
Convolutional layers
input_1
input_2
input_3
output_1
input_4
input_5
Convolutional layers
input_1
input_2
input_3
output_1
input_4
input_5
output_2
Step 2
Convolutional layers
input_1
input_2
input_3
input_4
input_5
output_3
step 3
output_1
output_2
Deep learning for images
32 px
32 px
Source: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture6.pdf
32 px
32 px
Input Image
CNN Kernel
Stride = 1
Same Padding
Stride = 1
Same Padding
Stride = 2
Same Padding
Stride = 2
Valid Padding
Max Pooling
Deep layers
Source: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture6.pdf
CNN Neurons
Size & Accuracy
Inception
Residual Connection
NASNet
Resources
Cheers!
Alvin Chan
Slides @
https://slides.com/alvinchan/team_jul19
CNN: May19 Team ppt
By Alvin Chan
CNN: May19 Team ppt
Team meeting 11 Jul 2019
- 918