Multiclass
Explore multiclass classification in neural networks using TensorFlow by learning how to implement one-hot encoding, add multiple hidden layers, and balance model complexity to reduce overfitting. Gain practical skills in configuring neural network layers for better training efficiency and accuracy.
We'll cover the following...
Chapter Goals:
- Learn about multiclass classification
- Understand the purpose of multiple hidden layers
- Learn the pros and cons of adding hidden layers
A. Multiclass classification
In the previous chapters we focused on binary classification, labeling whether or not an input data point has some class attribute (e.g. if it is in a circle or not). Now, we will attempt to classify input data points when there are multiple possible classes and the data point belongs to exactly one. This is referred to as multiclass classification.
The example is an extension of the previous circle example, but now there is an additional circle with radius 1 centered at the origin. The classes are now:
- 0: Outside both circles
- 1: Inside the smaller