Concern 191 · Working draft · editorial review in progress
Black-box neural nets
A black-box neural network is a model whose internal calculations are difficult for people to translate into an understandable account of a particular result.
Understanding the concern
A neural network learns many numerical relationships rather than following a short list of human-written rules. Knowing its design and training method does not necessarily tell us why one input produced one answer. This can make mistakes difficult to diagnose and decisions difficult to challenge.
Black box does not mean that nothing can be learned about the system. Testing, documentation, and interpretability methods can reveal useful evidence. The question is whether the explanation available is accurate and sufficient for the decision at hand, especially when someone's opportunities or safety are affected.
An example
A machine gives a score, but its operating manual does not explain why this particular application received it.
Illustrative unless identified as a documented case.
Words in plain English
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Training
- The process of using examples to shape how an AI model behaves. Learning patterns from material does not establish that the material is true or fair.
Evidence and its limits
NIST distinguishes explanation, meaning, accuracy and limits; opacity varies by model and use rather than being all-or-nothing.
NIST · IR 8312 · 2021 · Official research framework
Four Principles of Explainable Artificial Intelligence ↗ (opens in a new tab)Distinguishes explanation, meaningfulness, explanation accuracy and knowledge limits; these are separate evaluation questions.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What would an affected person need to understand in order to question this result?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Trustworthiness
Trustworthiness means giving people good reasons to rely on you. It grows when promises, actions, and evidence line up. With AI, a friendly voice or a famous brand is not enough: people need to know what was checked and what could still go wrong.
In practice, keep promises small enough to test, record mistakes, and tell people when the tool's limits affect them. If a service promises human review, make sure a person really has time and authority to review it.
Ask together: What would give the people affected a sound reason to trust this use?
Accountability
Accountability means being answerable for decisions and taking responsibility for repair. It requires more than saying that the software made the choice.
Name the person or team responsible, keep useful records, and give them authority to correct problems. Make the route to a complaint clear to the people affected.
Ask together: Who will answer for the outcome and help put things right?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.