Convolution
Explore the concept of convolution in convolutional neural networks, focusing on filters, kernel matrices, padding, and convolution layers. Understand how these components work together to extract features from image data, enabling the recognition of handwritten digits with practical TensorFlow implementation.
We'll cover the following...
Chapter Goals:
- Learn about convolutions
- Write a convolution layer for the neural network
A. Filters and kernels
As mentioned at the end of the Image Processing section, filters play a huge role in image recognition. We use filters to transform inputs and extract features that allow our model to recognize certain images. A very high-level example of this would be a curve detecting filter, which allows our model to distinguish between digits with curves (e.g. ) and digits without curves (e.g. ).
The weights of a filter are defined through a kernel matrix. The kernel is usually a square matrix and its weights are just floating point numbers.
...