liveBook · Manning

Model architecture

As explained in Delivering Machine Learning Projects: From design to deployment

A model architecture is the structural arrangement of components and connections that defines how a machine learning model processes inputs and produces outputs.

Model architecture is the arrangement of components and connections that determines how a machine learning model processes inputs and produces outputs. It is distinct from the surrounding system architecture, which must provide a way to run the model and connect it to other components. section 2.7.2

Before settling on a deployable solution, check both model requirements and the production environment. A high-level system design should identify the components needed for each function and expose missing infrastructure or skills early, without yet specifying every interaction. section 2.7.2

Smart building control

A building-control system needs sensor data, a database, a model execution environment, and a way to send control signals to actuators. It also needs to present events and decisions to users and owners. This describes the system around the model, not the model’s internal architecture. section 2.7.2

Record deployment constraints alongside model requirements:

  • Identify available data and processing systems, cloud policies, and legacy components that the solution must use or accommodate. section 2.3.2
  • Check whether required components are available and whether the team and client know how to commission and use them. section 2.7.2

How Delivering Machine Learning Projects: From design to deployment covers it

How deep it goes
Describes high-level system components and feasibility checks but does not specify model internals.
Examples
Uses a smart building system with sensors, a database, model execution, and actuators to illustrate deployment components.
What you can do after
Evaluate a high-level deployment design for missing components or skills before implementation.
How it connects
Connects model requirements with system architecture and nonfunctional requirements.

Also explained in

Compare how 22 books explain model architecture →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Delivering Machine Learning Projects: From design to deployment. The section links point to the parts of the book it draws on.