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

Made with Slides.com