AI & Machine Learning Vocabulary

A computing system inspired by biological neural networks

“The neural network learned to recognize faces with remarkable accuracy.”

Machine learning using neural networks with many layers

“Deep learning revolutionized image recognition and natural language processing.”

Training a model on labeled data with known outputs

“Supervised learning requires a dataset with correct answers for each example.”

Finding patterns in data without labeled examples

“Unsupervised learning discovered customer segments we hadn't considered.”

Learning through trial and error with rewards and penalties

“Reinforcement learning enabled the AI to master complex games.”

A neural network architecture using self-attention mechanisms

“Transformer models like GPT have transformed natural language processing.”

A dense vector representation of data in continuous space

“Word embeddings capture semantic relationships between terms.”

Adapting a pre-trained model for a specific task

“Fine-tuning the base model on our data improved accuracy significantly.”

Using a trained model to make predictions on new data

“Inference latency must be low for real-time applications.”

When an AI generates false or fabricated information

“The model's hallucination produced a convincing but entirely fictional citation.”

Crafting inputs to elicit desired outputs from AI models

“Effective prompt engineering dramatically improved the response quality.”

Breaking text into smaller units for processing

“Tokenization splits sentences into words or subword pieces.”

A technique allowing models to focus on relevant parts of input

“The attention mechanism helps the model understand context across long sequences.”

An optimization algorithm that minimizes error iteratively

“Gradient descent adjusts weights to reduce the loss function.”

When a model learns noise instead of the underlying pattern

“Overfitting caused the model to perform poorly on new data.”

When a model is too simple to capture the underlying pattern

“Underfitting resulted in poor performance on both training and test data.”

A parameter set before training begins, not learned from data

“Tuning hyperparameters like learning rate improved model performance.”

One complete pass through the entire training dataset

“The model converged after fifty epochs of training.”

The number of samples processed before updating the model

“Increasing batch size improved training stability but required more memory.”

A measure of how wrong the model's predictions are

“The loss function quantifies the difference between predictions and actual values.”

Prejudice in favor of or against one thing, person, or group

“We must ensure the AI model is free from bias.”

A process or set of rules to be followed in calculations

“The search algorithm ranks results by relevance.”