6
Deep Learning Reminders
Deep learning is the specific domain of machine learning based on neural networks. Deep learning is known to be particularly powerful with unstructured data, such as text, audio, and image, but can be useful for time series and structured data too. In this chapter, we will review the basics of deep learning, from a perceptron to training a neural network. We will provide recipes for training neural networks for three main use cases: regression, binary classification, and multiclass classification.
In this chapter, we’ll cover the following recipes:
- Training a perceptron
- Training a neural network for regression
- Training a neural network for binary classification
- Training a multiclass classification neural network
Get The Regularization Cookbook now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
