Finding the best neural architectures with AutoML
One way to think of machine learning algorithms is that they automate the process of learning relationships between given inputs and outputs. In traditional software engineering, we would have to explicitly write/code these relationships in the form of functions that take in input and return output. In the machine learning world, machine learning models find such functions for us. Although this automation speeds the process up, there is still a lot to be done. Besides mining and cleaning data, here are a few routine tasks to be performed to get those functions:
- Choosing a machine learning model (or a model family and then a model)
- Deciding on the model architecture (especially in the case of deep learning)
- Choosing hyperparameters
- Adjusting hyperparameters based on validation set performance
- Trying different models (or model families)
These are the kinds of tasks that justify the requirement...
