How deeply does Inside AI cover black box?

Explains the transparency and accountability problem but does not detail methods for interpreting model internals.

Black box

As explained in Inside AI

A black-box algorithm is an algorithm whose internal operations and reasoning are not readily interpretable from its inputs and outputs.

A black-box algorithm produces outputs whose internal operations and reasoning are not readily interpretable from its inputs and outputs. Deep-learning systems often create this transparency problem. section 11.17

High-stakes decisions

A military AI system cannot simply instruct personnel to “go do X” without explaining its reasoning. Similar concerns make black-box algorithms unsuitable for pivotal lending and criminal-justice decisions. section 9.4 section 11.17

Black-box systems create practical concerns when decisions carry serious consequences:

They hinder intellectual scrutiny, accountability, and confidence in decisions. section 9.4 section 11.17
They can conflict with regulations requiring explicability and transparency. section 11.17
They require careful testing and oversight before integration into critical functions. section 9.4

How Inside AI covers it

liveBook manning.com

Read Inside AI on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Get Programming: Learn to code with PythonA black box is an abstraction of a system whose internal steps are hidden while its inputs, outputs, and overall behavior remain visible.
liveBook manning.com

Ensemble Methods for Machine LearningA black-box model is a predictive model whose internal structure or decision process is difficult to understand directly, often requiring specialized explanation methods.
liveBook manning.com

Grokking StatisticsA black-box model is a model whose internal decision process is not readily understood or inspected by its users.
liveBook manning.com

Outlier Detection in PythonA black-box model is a predictive model whose internal decision process is not readily understandable from its inputs and outputs.
liveBook manning.com

Experimentation for EngineersA function or system whose internal process is not known while its inputs and outputs are observable.

Compare how 6 books explain black box →

Related concepts

surrogate modelused by · A surrogate model is an approximate model that estimates the behavior or outputs of a more complex, costly, or otherwise unavailable model, process, or function.
interpretabilitycontrasts with · Interpretability is the degree to which people can understand a model’s behavior, outputs, predictions, or the factors that produce them.
moduleequivalent to · A module is a distinct, bounded software unit that groups related code or functionality and provides an organizational or interaction boundary within a larger system.
partial dependence plotused by · A partial dependence plot shows a model's average predicted response as selected features vary, averaging over the values of the remaining features.
neural networkincludes · A neural network is a computational model of interconnected, parameterized units that learns transformations from inputs to outputs.

This explainer was generated by Manning's knowledge graph from the text of Inside AI. The section links point to the parts of the book it draws on.