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

Neural Networks (Basics)

A neural network, in the usual computer-science sense, is a composition of simple parameterized functions whose weights are set by an optimization procedure on data.

Overview

A neural network, in the usual computer-science sense, is a composition of simple parameterized functions whose weights are set by an optimization procedure on data.

It is not a brain. Those are metaphors. This wiki page stays with the computational object.

Definition

Units compute a weighted combination of inputs and pass it through a nonlinearity. Layers stack those units. Depth is a design choice, not a moral quality.

Training adjusts weights to reduce a loss on a dataset. Inference uses a frozen (or slowly updated) set of weights on new inputs.

Deep learning is a popular name for training deeper networks with more data and compute. The definition of a network does not require the adjective “deep.”

Why the distinction matters

Metaphors hide failure modes. A network can be accurate on a test file and still fail when a camera angle changes.

Capacity lets networks fit complicated functions and also fit noise. Regularization and evaluation belong in the same conversation as architecture cartoons.

Core pieces

Units and layers.

Weights (parameters) updated in training.

A loss and an optimizer.
Data pipelines that can leak or shift.

A deployment context the cartoon does not show.

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

Worked intuition

Think of a stack of spreadsheet operations, each a little nonlinear, repeated millions of times with coefficients tuned on examples. That is closer than a neuron documentary.

If you remove the data, the architecture is an empty form. Papers that show only a diagram have not yet shown a system.

Common confusions

“Neural” meaning biological understanding.

Assuming more layers always help.

Equating a demo with a measured task.
Hiding the training data when making a capability claim.

Limits

Networks do not magically know the causal structure of the world. They fit correlations in the file they saw.

They can be expensive to train and to evaluate honestly. Cost is part of the method, not an afterthought.

Practical checks

Name the task and the split.

Compare against a simple baseline.
Look at errors, not only a leaderboard number.

Read whether the paper’s test set was reused as a development set for years.

What a careful page refuses

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

They can be expensive to train and to evaluate honestly. Cost is part of the method, not an afterthought.

See also: training and inference, overfitting, evaluation metrics. Equations belong in a textbook; this is an overview.

Glossary

Parameter / weight: a number the training procedure sets.

Activation: the nonlinearity after a linear combination.
Architecture: the pattern of units and connections, before weights are set.

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 need a GPU to understand this page?

No.

Are transformers neural networks?

Yes, they are a family of architectures.

Is a bigger network smarter?

It may fit more functions. Smarter is not a defined metric here.

Why this page exists in the collection

Neural Networks (Basics) 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 basics of neural networks as layered functions with learned weights, not as brains.

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, neural networks, deep learning. 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. “Units and layers.” is the kind of object this page is willing to talk about because it can be pointed at.

Another object on the table is “Weights (parameters) updated in training.”. 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. Units and layers. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. Weights (parameters) updated in training. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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 loss and an optimizer. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. Data pipelines that can leak or shift. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. A deployment context the cartoon does not show. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. “Neural” meaning biological understanding. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. Assuming more layers always help. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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. Equating a demo with a measured task. Treat this as something you could put on a table in a meeting about Neural Networks (Basics). 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 Neural Networks (Basics) 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, neural networks, deep learning becomes wallpaper.

Consider a week in which Units and layers. is supposed to happen, but Weights (parameters) updated in training. 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 Neural Networks (Basics).

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 Neural Networks (Basics) 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 Units and layers.. 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 Weights (parameters) updated in training.. 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 loss and an optimizer. 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 Neural Networks (Basics) 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 Units and layers. 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 Neural Networks (Basics) is actually asking.

Week 2: Inventory current documents related to Computer science, Artificial intelligence, neural networks, deep learning.
Week 3: Pick one artifact as concrete as: Units and layers..

Week 4: Write the non-claims in language copied from this page’s limits.

Week 5: Run a tiny version that still includes Weights (parameters) updated in training..
Week 6: Log skips; do not hide them in a highlight reel.

Week 7: Repair the calendar so A loss and an optimizer. 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 Neural Networks (Basics), 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 Neural Networks (Basics).
The dated lead as published: Page type: Article / Wiki · Category: Computer science / Artificial intelligence

A list of in-scope objects, starting with Units and layers..

A list of out-of-scope requests (advice, rankings, invented rates).
Names of owners for Weights (parameters) updated in training. 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 Neural Networks (Basics).

Pretty templates are optional. Dates and owners are not.

Error catalog

Hiding the collision between Weights (parameters) updated in training. and a hard calendar event.

Asking the page to do casework, medical advice, or live filings.
Inventing a percentage because a meeting wanted a percentage.

Publishing identifiable information that the method said to remove.

Mixing page type Article / Wiki with a different genre in the same citation.
Scaling across all of computer science before a four-week trial exists.

Citing an unofficial look-alike domain as the primary source.
Treating Units and layers. as optional theatre while keeping the slogan.

Quoting Neural Networks (Basics) as if it measured an outcome it explicitly refused to measure.

Letting an undated PDF outrank the dated page.

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 Neural Networks (Basics) is to reread the non-claims before you present.

Glossary for this page

Neural Networks (Basics) — 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: Units and layers.

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 Weights (parameters) updated in training. 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 Neural Networks (Basics) without adjectives?

Can you point at Units and layers. 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, neural networks, deep learning?

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 Neural Networks (Basics), not a generic poster.

What “good enough” looks like without fake scores

Good enough for Neural Networks (Basics) 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 Units and layers. happened.

It is certainly not a claim that Computer science, Artificial intelligence, neural networks, deep learning 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 Neural Networks (Basics), 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 Units and layers. 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.

Neural Networks (Basics) 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 Neural Networks (Basics) 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.

Neural Networks (Basics) 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

Limitations of Current AI Systems — Wiki-style catalog of limitations: distribution shift, hallucinations in generation, and cost of evaluation.

Reinforcement Learning (Introduction) — Wiki introduction to reinforcement learning: agents, rewards, and why the reward is the hard part.
Feature Representation — Wiki-style page on feature representation: how raw inputs become the vectors a model consumes.

Computer Vision (Introduction) — Wiki introduction to computer vision: making predictions from images or video, with task names and failure modes.

Evaluation Metrics in Machine Learning — Wiki overview of evaluation metrics: accuracy is not always the right score, and the split matters.

These titles share the Computer science section with Neural Networks (Basics). 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

Neural Networks (Basics) is a Article / Wiki page in Computer science / Artificial intelligence. Its job is: Wiki-style basics of neural networks as layered functions with learned weights, not as brains.

Do the concrete thing (Units and layers.). Write down what you will not claim. Date the file. Name an owner for Weights (parameters) updated in training..

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 Neural Networks (Basics), 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.