Page type: Article / Wiki · Category: Computer science / Artificial intelligence

Feature Representation

A feature is a measured or computed property used as input. Representation is the choice of those properties — including learned embeddings in modern systems.

Overview

A feature is a measured or computed property used as input. Representation is the choice of those properties—including learned embeddings in modern systems.

Classic features encode human hypotheses. Learned hidden layers can act as features and are harder to inspect.

Definition

Tabular work often starts with counts, ratios, and indicators. They are inspectable. They also encode choices (what you did not count).

Representation learning asks the training procedure to invent coordinates. That can work well and still hide the cue the model used (background, watermark, filename).

This wiki page is about the idea, not a list of vector databases.

Why the distinction matters

If a feature contains the label (target leakage), metrics become theatre.

If a learned representation clusters by hospital rather than by disease, downstream classifiers may learn the hospital.

Core pieces

Raw observations.

A transformation (hand-built or learned).
A vector or sequence the model consumes.

A story you can tell—or cannot—about what the coordinates mean.

If a tutorial skips these pieces and jumps to a demo, you are watching a product, not reading a definition.

Worked intuition

Bag-of-words is a representation: counts of tokens. It forgets order. That is a limitation you can state in one sentence.

An embedding is also a representation: a point in a space. Neighbours can be meaningful or embarrassing. Inspect them.

Common confusions

Calling any vector an “understanding.”
Normalizing with the test set included.
Leaving IDs and timestamps in the matrix by accident.

Assuming a pretrained embedding matches your domain.

Limits

No representation is complete. Information is thrown away on purpose or by accident.

Learned features can be unstable across retrains if you do not control seeds and data order.

Practical checks

List the columns you feed the model.
Ask whether each would be available at prediction time.
Try a simple feature set as a baseline.

Inspect nearest neighbours of embeddings.

What a careful page refuses

It refuses fake precision, fake timelines, and vendor adjectives that are not part of the definition.

Learned features can be unstable across retrains if you do not control seeds and data order.

See also: data leakage, neural networks, supervised learning.

Glossary

Embedding: a learned vector for an object.

One-hot: a sparse indicator representation.
Feature leak: a column that smuggles the target.

How to use this wiki page

Read the definition, then the confusions, then the checks. The FAQ is last on purpose: it should not replace the definition.

If you cite this page, cite the limitation that matches your use, not only the first sentence.

FAQ

Do I always need embeddings?

No. For many tables, two ratios beat a mystery vector.

Are features the same as data?

Data are what you collected. Features are what you computed to feed the model.

Can I interpret a deep feature?

Sometimes partially. Do not bluff.

Why this page exists in the collection

Feature Representation sits in a Article / Wiki slot with category Computer science / Artificial intelligence. That pairing is not decoration: readers should be able to tell a research note from a listing, and a home page from a wiki overview, before they quote a sentence out of context.

The one-line job of the page is this: Wiki-style page on feature representation: how raw inputs become the vectors a model consumes.

If you only remember one constraint, remember the lead: Page type: Article / Wiki · Category: Computer science / Artificial intelligence

The page is written for computer science readers who will either teach from it, cite it, or use it as a map. It is not written as a press release and it does not invent measurements that were not collected.

Scope and non-scope, stated slowly

In scope: the practice and documents around Computer science, Artificial intelligence, features, representation. Out of scope: ranking offices, promising outcomes, or turning a classroom into a market.

A useful test is whether a sentence still holds if you remove adjectives. “Raw observations.” is the kind of object this page is willing to talk about because it can be pointed at.

Another object on the table is “A transformation (hand-built or learned).”. If your question is actually about something else—private casework, live filings, clinical advice, or product pricing—stop and go to a qualified channel.

Non-scope also includes gossip about named minors, unnamed “secret” datasets, and any request to hide a limitation because it makes the story less tidy.

Walking through the checklist in full sentences

Item 1. Raw observations. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 2. A transformation (hand-built or learned). Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 3. A vector or sequence the model consumes. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 4. A story you can tell—or cannot—about what the coordinates mean. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 5. Calling any vector an “understanding.” Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 6. Normalizing with the test set included. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 7. Leaving IDs and timestamps in the matrix by accident. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

Item 8. Assuming a pretrained embedding matches your domain. Treat this as something you could put on a table in a meeting about Feature Representation. If you cannot point to an artifact, a date, or a named owner for it, it is not yet evidence; it is a wish. Write the missing piece before you scale the idea across a year of computer science work.

A longer narrative of the problem

People usually meet Feature Representation as a short slogan. The slogan travels faster than the log. Then a team is surprised when a term ends and the only remaining trace is a folder of unused files.

The longer story is operational. Someone has to name the text, the hour, the owner, and the thing students or readers will produce. Without that, Computer science, Artificial intelligence, features, representation becomes wallpaper.

Consider a week in which Raw observations. is supposed to happen, but A transformation (hand-built or learned). is competing for the same hour. The honest publication names the collision instead of adding a new poster.

Consider also the quiet failure: the work is done, but nobody can find it next month because the filename is “final-final-v3”. Documentation is part of the method, not an afterthought for Feature Representation.

None of this requires a new brand of software. It requires a calendar, a named artifact, and a sentence about what will not be claimed. That is the tone of this page.

Worked scenario A: a careful trial

A small team decides to trial one idea from Feature Representation for four weeks, not a year. They write the question in one sentence copied from the lead: Page type: Article / Wiki · Category: Computer science / Artificial intelligence

Week 1 is setup: they identify the artifact that will count as “done.” It should be as concrete as Raw observations.. They also write the exclusion: they will not claim effects they did not measure.

Week 2 is the first real run. They expect friction around A transformation (hand-built or learned).. They log what was skipped and why, in language a substitute colleague could understand.

Week 3 is a repair week. They drop one extra ambition so A vector or sequence the model consumes. can actually finish. Repair is not failure; it is the method.

Week 4 is a write-up of two pages: what happened, what they will keep, what they will not repeat. They cite this page as a map, not as proof.

Worked scenario B: the over-scoped version that fails

A different team announces Feature Representation as a whole-institution priority in the same week they have reports, a public event, and a system migration. Nothing is named as the single artifact.

They create a dashboard. The dashboard cannot answer whether Raw observations. occurred. It can only show that a file was uploaded.

By week six the original lead—Page type: Article / Wiki · Category: Computer science / Artificial intelligence—is no longer mentioned in meetings. People mention “the initiative.” Initiatives do not leave notebooks.

The recovery is embarrassing and simple: shrink back to one unit, one owner, one collected task, and the limits already written on this page.

A twelve-week implementation sketch

Week 1: Name the question Feature Representation is actually asking.
Week 2: Inventory current documents related to Computer science, Artificial intelligence, features, representation.
Week 3: Pick one artifact as concrete as: Raw observations..

Week 4: Write the non-claims in language copied from this page’s limits.
Week 5: Run a tiny version that still includes A transformation (hand-built or learned)..
Week 6: Log skips; do not hide them in a highlight reel.

Week 7: Repair the calendar so A vector or sequence the model consumes. can finish.
Week 8: Share a two-page note with a colleague who was not in the room.
Week 9: Decide whether to stop, continue, or redesign.

Week 10: If continuing, freeze the definition of “done” for the next month.
Week 11: Check that citations still point at dated sources, not at rumours.
Week 12: Retire leftover files that contradict the lead: Page type: Article / Wiki · Category: Computer science / Artificial intelligence

This calendar is a sketch for Feature Representation, not a contract. If a public deadline in computer science collides with a week, move the week—do not pretend both happened.

If you skip logging, you are back to slogans. The sketch exists to make skipping visible.

Documentation pack

A one-sentence question taken from Feature Representation.
The dated lead as published: Page type: Article / Wiki · Category: Computer science / Artificial intelligence
A list of in-scope objects, starting with Raw observations..

A list of out-of-scope requests (advice, rankings, invented rates).
Names of owners for A transformation (hand-built or learned). and a substitute if they are away.
A filename convention that includes a date.

A citation line that includes limits.
Links to sibling pages in Computer science.
A retirement note for superseded files.

A short glossary so newcomers do not invent synonyms.

If the pack cannot fit in a folder a new colleague can open in five minutes, it is too baroque for Feature Representation.

Pretty templates are optional. Dates and owners are not.

Error catalog

Treating Raw observations. as optional theatre while keeping the slogan.
Citing an unofficial look-alike domain as the primary source.

Scaling across all of computer science before a four-week trial exists.
Quoting Feature Representation as if it measured an outcome it explicitly refused to measure.
Letting an undated PDF outrank the dated page.

Inventing a percentage because a meeting wanted a percentage.
Mixing page type Article / Wiki with a different genre in the same citation.
Publishing identifiable information that the method said to remove.

Hiding the collision between A transformation (hand-built or learned). and a hard calendar event.
Asking the page to do casework, medical advice, or live filings.

Each error is recoverable if you name it early. It is expensive if it becomes the public story of the work.

The cheapest prevention for Feature Representation is to reread the non-claims before you present.

Glossary for this page

Feature Representation — the document you are reading, with page type Article / Wiki and category Computer science / Artificial intelligence.
Artifact — a thing you could hold up, such as: Raw observations.

Lead — the opening claim: Page type: Article / Wiki · Category: Computer science / Artificial intelligence
Limit — a sentence that forbids a nicer claim than the method can carry.
Computer science — the home section of this page, not a licence to speak for every office in the world.

Date — the difference between a publication and a rumour.
Owner — the person who can change A transformation (hand-built or learned). without a mystery committee.

Sibling page — another title in the same section, listed below when available.

Reader checklist before you cite or adopt

Can you state the job of Feature Representation without adjectives?
Can you point at Raw observations. in a real folder or classroom?

Is every number (if any) sourced, or did you add none because none were collected?
Does the citation include the limit that belongs with Computer science, Artificial intelligence, features, representation?
Would a substitute colleague know what “done” looks like next week?

Have you avoided promising a ranking, a cure, or a guaranteed placement?
Is the page type still honestly Article / Wiki?
Is the category still honestly Computer science / Artificial intelligence?

If you fail two checks, do not cite yet. Fix the file or shrink the claim.

This checklist is part of Feature Representation, not a generic poster.

What “good enough” looks like without fake scores

Good enough for Feature Representation is a dated artifact, a named owner, and a next step that survived contact with a calendar.

It is not a launch photograph. It is not a dashboard that cannot answer whether Raw observations. happened.

It is certainly not a claim that Computer science, Artificial intelligence, features, representation has been “solved.” Solved is a word this collection tries not to use.

If you need a number, collect one that matches the question, then publish the instrument. Until then, write in sentences.

Teaching notes

If you teach Feature Representation, give students a primary object first: a form, a lab page, a syllabus line, a model card, a gazette. Then give them this page as a map of how to talk about that object.

A good thirty-minute seminar: (1) read the lead, (2) mark the non-claims, (3) try to apply Raw observations. to a public document you did not write.

Do not ask students to harvest private data. Do not ask them to impersonate an office. Do not ask them to produce a rate you would not defend.

Assessment can be a two-page memo that cites this page and one official source, with the date of capture written on the first line. That is enough to see whether computer science literacy is happening.

For information officers and editors

If you maintain public pages in computer science, steal the habits, not the adjectives: date, owner, next step, non-claim.

Feature Representation will age. Put a review month on it. If you cannot review it, do not let it remain the featured link.

When legal, medical, or emergency readers arrive, your first job is to send them to a qualified channel. Education pages that pretend to be those channels cause harm.

When you quote Feature Representation in a newsletter, quote a limit next to the attractive sentence. Attractive sentences travel; limits do not, unless you chain them.

Notes on wiki genre

A wiki overview defines, distinguishes, and lists failure modes. It does not sell a library or a timeline to imaginary general intelligence.

Feature Representation should be cited for the distinction it draws, not as proof that a product works.

If a tutorial skips evaluation and jumps to a demo, it is not this page.

Update the glossary if a word starts meaning three things in your course. Do not pretend the field is settled.

Related pages in this collection

Supervised Learning — Wiki-style overview of supervised learning: labeled examples, a model, and a test the labels did not train on.
Unsupervised Learning — Wiki article on unsupervised learning: finding structure in data without task labels.

Model Cards and Model Documentation — Wiki page on documenting models: intended use, data, metrics, and out-of-scope uses.
Natural Language Processing (Introduction) — Wiki introduction to NLP as computational work on text and speech, with tasks and limits.
Training and Inference — Wiki article distinguishing training (fitting weights) from inference (using a fixed model).

These titles share the Computer science section with Feature Representation. They are not duplicates. Read the page type before you mix citations.

If a sibling contradicts this page, prefer the dated limits on each page rather than blending them into a mash-up claim.

Plain-language recap

Feature Representation is a Article / Wiki page in Computer science / Artificial intelligence. Its job is: Wiki-style page on feature representation: how raw inputs become the vectors a model consumes.

Do the concrete thing (Raw observations.). Write down what you will not claim. Date the file. Name an owner for A transformation (hand-built or learned)..

Do not invent rates. Do not use this page as a clinic, a court, or a marketplace. Do not strip the limits off the attractive sentences.

If you do only that, the collection has done enough work for one reading.

Versioning and review

When you locally adapt Feature Representation, keep a version line: date, editor, what changed, what did not.

A change to the lead is a new document. A change to an example can be a minor note.

Review at least when the surrounding computer science calendar jumps (new term, new statute text, new dataset version).

If nobody is named to review it, the page is already on its way to becoming folklore.