liveBook · Manning

Target function

A target function is an unknown input-output mapping representing the desired behavior that a predictive model aims to approximate.

How 3 Manning books explain it

Math and Architectures of Deep Learning

The unknown function expressing desired input-output behavior that a model aims to approximate.

How it is used
Frames intelligent tasks as unknown input-output mappings that neural networks can approximate.
How deep it goes
Defines notation, variable types, and neural-network approximation, but stops short of detailing training procedures.
Examples
Uses stock-selling decisions with prices and expert advice as inputs and binary sell-or-hold outputs.
What you can do after
Understand how real-world decisions become mathematical mappings that neural networks can approximate.

Read how Math and Architectures of Deep Learning explains target function →

Evolutionary Deep Learning: Genetic algorithms and neural networks

A target function is a mathematical function that an evolutionary program is intended to reproduce or approximate.

How it is used
Uses a desired mathematical relationship to guide evolutionary search toward an approximating expression.
How deep it goes
Defines a linear target, implements its fitness comparison, and exercises changes in complexity without deriving approximation theory.
Examples
Uses f(x1) = 6x1 + 22, sample-input predictions, mean absolute error, and a simplified evolved equation.
What you can do after
Build it from scratch with Geppy by defining a target, evolving candidate expressions, measuring error, and inspecting the best result.

Read how Evolutionary Deep Learning: Genetic algorithms and neural networks explains target function →

Build AI Drug Discovery Pipelines

A target function is the unknown input-output mapping that defines the true outcome of a prediction task.

How it is used
Frames supervised prediction as approximating an unknown ground-truth mapping from compound features to biological outcomes.
How deep it goes
Defines the mapping and connects it to training, optimization, generalization, and frozen-weight inference.
Examples
Uses molecular features and experimentally determined hERG-blocking labels for druglike compounds.
What you can do after
Evaluate/understand how trained models approximate biological ground truth and generate predictions for unseen compounds.

Read how Build AI Drug Discovery Pipelines explains target function →

Related concepts

Questions about target function

What is target function?

A target function is an unknown input-output mapping representing the desired behavior that a predictive model aims to approximate.

Which Manning books explain target function?

Math and Architectures of Deep Learning, Evolutionary Deep Learning: Genetic algorithms and neural networks and Build AI Drug Discovery Pipelines.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.