%%html
<!-- The customized css for the slides -->
<link rel="stylesheet" type="text/css" href="../styles/python-programming-introduction.css"/>
<link rel="stylesheet" type="text/css" href="../styles/basic.css"/>
<link rel="stylesheet" type="text/css" href="../../assets/styles/basic.css" />

43.20. Convolutional Neural Network#

43.20.1. The Brain#

  • When we see something, we label every object based on what we have learned in the past

  • While vision starts in the eyes, the actual interpretation of what we see happens in the brain, in the primary visual cortex

  • The deeply complex hierarchical structure of neurons and connections in the brain play a major role in this process of remembering and labelling objects

43.20.2. From Brain to Convolutional Neural Networks#

  • Convolutional Neural Networks are inspired by the brain

  • The simple cells activate, for example, when they identify basic shapes as lines in a fixed area and a specific angle. The complex cells have larger receptive fields and their output is not sensitive to the specific position in the field

  • The concept of hierarchy plays a significant role in the brain

  • In 1998, Convolutional Neural Networks were introduced in a paper by Bengio, Le Cun, Bottou and Haffner

43.20.3. How a computer sees an image#

43.20.4. Kernel (image processing)#

43.20.5. CNN architecture (1/3)#

43.20.6. CNN architecture (2/3)#

43.20.7. CNN architecture (3/3)#

43.20.8. Time to play!#

43.20.9. Feature extraction#

source

43.20.10. Padding#

43.20.11. Pooling#

43.20.12. Flattening#

source

43.20.13. Full Connection#

source

43.20.14. Acknowledgement#

https://www.freecodecamp.org/news/an-intuitive-guide-to-convolutional-neural-networks-260c2de0a050/