The Google Machine Learning Glossary is Google for Developers’ maintained, web-based reference for machine-learning terms and definitions. It gives a quick, plain-language starting point for unfamiliar concepts, then connects readers to related entries, courses, walkthroughs, and engineering guides. The collection ranges from fundamentals to specialized subjects such as TensorFlow, generative AI, evaluation metrics, responsible AI, Google Cloud, clustering, and agentic systems.
What the Google Machine Learning Glossary is
The glossary is a terminology reference rather than a complete course or textbook. Each entry explains a concept in the context of machine-learning systems and may point to related terms or deeper technical material. That makes it useful when you encounter an unfamiliar word in a paper, code sample, model card, course, or Google Cloud product guide.
Google describes the editorial process this way: “A Google team of technical writers, researchers, and software engineers writes and reviews each definition.” The result is a reference intended for both newcomers who need a dependable starting definition and practitioners who need Google’s terminology in a particular technical or product context.
How the glossary is organized
You can narrow the collection into topic subglossaries instead of browsing one undifferentiated list. The most useful ways to choose an entry are its audience level, technical domain, and depth.
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minute#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
| View or comparison axis | What it helps you find | Typical use |
|---|---|---|
| Audience level | Fundamentals versus advanced or specialized concepts | Start with core vocabulary before reading research or implementation details |
| Domain | Fundamentals, generative AI, metrics, responsible AI, TensorFlow, Google Cloud, clustering, and agentic concepts | Stay within the vocabulary of a course, project, or product area |
| Depth | A short definition versus examples, equations, diagrams, and cross-references | Get a quick meaning first, then investigate how the concept works |
Topic filtering is especially valuable for terms that mean different things in different settings. A metrics entry may define a score and its calculation, while a responsible-AI entry may define a fairness condition and its implications.
Representative machine-learning terms and definitions
Machine learning
Google defines machine learning as a program or system that trains a model from input data. After training, the model makes useful predictions on new data drawn from the same distribution. The definition emphasizes both stages: learning from examples and applying what was learned to later inputs.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
Model
A model is a mathematical construct that processes input data and returns output. Its structure and parameters determine how it produces predictions. In practice, “model” can refer to the learned artifact used for inference, not just the algorithm or software surrounding it.
Hyperparameter
A hyperparameter is a variable set by a person or tuning service across successive training runs. Learning rate is a common example. Hyperparameters differ from parameters: the training process learns parameters from data, whereas a practitioner chooses or tunes hyperparameters.
Recommended Free Tools
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
Attention
Attention is a neural-network mechanism that indicates the importance of a word or part of a word when processing an input. The glossary connects the concept to self-attention and Transformer architectures, where relationships among tokens help the network represent context.
Differential privacy
Differential privacy is an anonymization approach that adds noise during training to reduce the exposure of information about individuals represented in the training data. It addresses privacy risk in the learning process; it is not a guarantee that every possible disclosure risk disappears.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Demographic parity
Demographic parity is a fairness condition in which classification results do not depend on a specified sensitive attribute. Evaluating it requires stating which attribute and which outcome are being compared; the condition does not, by itself, establish that a model is fair in every other respect.
Average precision at k
Average precision at k is a ranking and evaluation metric documented in the metrics subglossary. It combines the precision of the top-ranked results at each relevant position up to k. The glossary provides the formula and worked examples, which are important because the metric’s interpretation depends on the cutoff and relevance judgments.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
How to compare two terms without mixing their meanings
When two entries sound similar, compare them along four questions:
- Scope: Does one term describe a broad system or a narrower mechanism?
- Role: Is it an input, output, model component, data concept, metric, or responsible-AI condition?
- Stage: Does it apply during data preparation, training, evaluation, or inference?
- Evidence: Is the term defined by an equation, an architectural example, a behavioral requirement, or a privacy objective?
For example, a hyperparameter is a training-control variable, while a model parameter is learned during training. Attention is a model mechanism, whereas average precision at k evaluates ranked outputs. Differential privacy concerns protection of information about people in training data; demographic parity concerns the relationship between predictions and a specified sensitive attribute.
A practical way to use the glossary
- Start with the exact term. Search for the word as it appears in your paper, notebook, API documentation, or error message.
- Read the definition before the linked material. Identify the input, output, role, and stage described by the entry.
- Open cross-references. Follow linked concepts when the definition relies on an overloaded term such as “bias,” “parameter,” or “embedding.”
- Choose the relevant subglossary. Use Fundamentals for first principles; use metrics, generative AI, responsible AI, TensorFlow, or Google Cloud views when your question is domain-specific.
- Move to instruction. Use the glossary alongside Google’s courses, walkthroughs, and engineering guides. The glossary supplies vocabulary; those materials supply procedures, code, and longer explanations.
- Check the surrounding context. A definition may be intentionally concise. Read the linked example, equation, diagram, or guide before applying a term to a production decision.
How current the definitions are
The glossary is a living reference. Google says it releases batches of new terms three to four times a year and frequently makes minor changes to existing definitions. Consequently, a saved quotation or screenshot can become outdated; when publishing one, record the access date (September 30, 2026) and verify the entry again before relying on it.
There is no stable, officially published total entry count or readership figure to use as a measure of the glossary’s size. Its value is the maintained terminology and the links into deeper learning material, not a claimed number of entries.
When the glossary is the right resource
- Use it first when a term is unfamiliar or appears to have several technical meanings.
- Use it for comparison when you need to separate a model component from a metric, a training setting from a learned parameter, or a privacy concept from a fairness concept.
- Pair it with a course or guide when you need implementation steps, mathematical background, code, or deployment advice.
- Do not treat a one-sentence entry as a complete design specification. Production choices still require details about data, evaluation, threat models, and operating constraints.
Bottom line for learners and practitioners
The Google Machine Learning Glossary is best understood as a maintained definitions layer for the wider Google machine-learning learning ecosystem. Begin with the Fundamentals entries, filter into the specialized subglossary that matches your work, and use the cross-references and linked courses to move from a term’s meaning to its practical application.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
