Technology Vocabulary

#401

Artificial intelligence

Example sentences

1. Artificial intelligence allows machines to perform tasks that usually need human thinking.
2. The company uses artificial intelligence to answer common customer questions.
3. Artificial intelligence can help people, but its results should still be checked.

#

#402

Machine learning

Example sentences

1. Machine learning helps computers learn patterns from data.
2. The email service uses machine learning to detect spam.
3. A machine learning system usually improves when it receives better data.

#

#403

Deep learning

Example sentences

1. Deep learning uses large neural networks to learn complex patterns.
2. Deep learning can recognize objects in photographs.
3. Training a deep learning system may require powerful computers.

#

#404

Neural network

Example sentences

1. A neural network learns by changing connections between many simple units.
2. The neural network identified handwritten numbers.
3. The team trained the neural network with thousands of examples.

#

#405

Artificial neuron

Example sentences

1. An artificial neuron receives values and produces an output.
2. Many artificial neurons work together in a neural network.
3. The artificial neuron gives more importance to some inputs than others.

#

#406

Model

Example sentences

1. The model predicts whether a customer may leave the service.
2. The team tested the model with new data.
3. A model can give poor results when its training data is weak.

#

#407

Algorithmic model

Example sentences

1. An algorithmic model uses mathematical rules to represent a problem.
2. The bank created an algorithmic model to estimate credit risk.
3. The algorithmic model was simpler than the real-world situation.

#

#408

Training

Example sentences

1. Training teaches a machine learning system from examples.
2. The training took several hours on a powerful computer.
3. Better training data can produce a more useful model.

#

#409

Inference

Example sentences

1. Inference happens when a trained model produces an answer.
2. The phone performs inference to recognize a face.
3. Fast inference is important for real-time applications.

#

#410

Training dataset

Example sentences

1. The training dataset contains examples used to teach the model.
2. The training dataset included images from many different places.
3. Errors in the training dataset can affect the final model.

#

#411

Validation dataset

Example sentences

1. The validation dataset helps developers choose and improve a model.
2. The team checked performance on the validation dataset after each change.
3. The validation dataset should be separate from the training data.

#

#412

Test dataset

Example sentences

1. The test dataset measures how well the final model handles unseen examples.
2. The model reached high accuracy on the test dataset.
3. The team used the test dataset only after training was complete.

#

#413

Feature

Example sentences

1. A feature is an input used by a machine learning model.
2. Age was one feature in the prediction system.
3. The team removed a feature that did not improve the result.

#

#414

Label

Example sentences

1. The label is the correct answer linked to a training example.
2. Each image had a label showing the type of animal.
3. Incorrect labels can confuse the model during training.

#

#415

Supervised learning

Example sentences

1. Supervised learning uses examples with known answers.
2. The team used supervised learning to classify customer messages.
3. In supervised learning, each training item usually has a label.

#

#416

Unsupervised learning

Example sentences

1. Unsupervised learning searches for patterns without known answers.
2. The company used unsupervised learning to group similar customers.
3. Unsupervised learning may reveal patterns that people did not expect.

#

#417

Reinforcement learning

Example sentences

1. Reinforcement learning teaches a system through rewards and penalties.
2. The robot used reinforcement learning to improve its movements.
3. In reinforcement learning, the system learns from the results of its actions.

#

#418

Classification

Example sentences

1. Classification places an item into one of several groups.
2. The model performs classification on emails as spam or not spam.
3. Image classification can identify the main object in a picture.

#

#419

Regression

Example sentences

1. Regression predicts a number instead of a category.
2. The company used regression to estimate next month's sales.
3. The regression model studied the connection between price and demand.

#

#420

Clustering

Example sentences

1. Clustering groups similar items without using fixed labels.
2. The analyst used clustering to find customer groups.
3. Clustering placed users with similar behavior together.

#