chapter one

1 Designing Modern Machine Learning

 

This chapter covers

  • Evolving from classical AI to cutting-edge approaches, including model fusion and amalgamation
  • Designing pipelines
  • Applying design patterns to deep learning
  • Introducing the procedural reuse design pattern for modeling neural networks

The latest revolution in deep learning is at the macro level rather than the micro level, with the introduction of an approach that I coined while working at Google Cloud AI as model amalgamation. In this approach, models are broken down into composable units which share and adapt components to achieve different objectives with the same initial data. The components are interconnected in a variety of connectivity patterns, where each component “learns” communication interfaces between the models through design, without the necessity of a backend application. In addition, the model amalgamation can be used to train IoT devices for data enrichment, turning IoT sensors from static to dynamically learning devices – a technique called model fusion. Amalgamation is providing the means for putting AI into production at a scale and operational complexity not conceivable in 2017, when the push into production first started to emerge.

1.1    The Evolution in Machine Learning Approaches

1.1.1   Classical AI vs Narrow AI

1.1.2   Next steps in computer learning

1.2    Pipeline Design in Production

1.2.1   Machine Learning as a Pipeline

1.2.2   Machine Learning as a CI/CD Production Process

1.2.3   Model Amalgamation in Production

1.3    The Procedural Reuse Design Pattern

1.4    Summary