In machine learning, a classifier assigns a class label to a data point. For example, an image classifier produces a class label (e.g, bird, plane) for what objects exist within an image. A convolutional neural network, or CNN for short, is a type of classifier, which excels at solving this problem! A CNN is a neural network: an algorithm used to recognize patterns in data. Neural Networks in general are composed of a collection of neurons that are organized in layers, each with their own learnable weights and biases. Let’s break down a CNN into its basic building blocks. A tensor can be thought of as an n-dimensional matrix. In the CNN above, tensors will be 3-dimensional with the exception of the output layer. A neuron can be thought of as a function that takes in multiple inputs and yields a single output. The outputs of neurons are represented above as the red → blue activation maps.
Features
- A layer is simply a collection of neurons with the same operation
- Kernel weights and biases
- A CNN conveys a differentiable score function
- Class scores in the visualization on the output layer.
- CNNs utilize a special type of layer
- In CNN Explainer, you can see how a simple CNN can be used for image classification
- The input layer (leftmost layer) represents the input image into the CNN