✨ Improving Neural Networks used in Computer Vision problems

This folder contains theoric details about CNNs

πŸ“š Important Terms



πŸ’« Convolutoin

Applying some filter on an image so certain features in the image get emphasized

πŸŒ€ Pooling

A way of compressing an image

πŸ”· 2*2 max pooling

For every 4 neighbor pixels the biggest one will survive

β­• Padding

Adding additional border(s) to the image before convolution

πŸ’« Notes on performance

  • Training speed of a CNN is too slower than plain NN because of its computational complexity 🐒

🧐 References

Last updated