Essential terms every AI learner should know.
A subset of AI where systems learn patterns from data to make decisions or predictions without being explicitly programmed for each task.
Training a model on labeled data — each example has an input and a known correct output. The model learns to map inputs to outputs.
Training on unlabeled data — the model finds hidden patterns or groupings on its own.
An agent learns by interacting with an environment, receiving rewards for good actions and penalties for bad ones, optimizing for maximum cumulative reward.
When a model learns the training data too well — including noise and outliers — and performs poorly on new, unseen data.
When a model is too simple to capture the patterns in the data, performing poorly on both training and test data.
A field of AI focused on enabling computers to understand, interpret, and generate human language.
The smallest unit of text a model processes. Tokens can be words, subwords, or characters. A single word may be split into multiple tokens.
A numerical representation of text (or other data) in a continuous vector space, where similar items are closer together.
The maximum number of tokens a model can process at once — both input and output combined.
Restating text in different words while preserving the original meaning. LLMs excel at this task.
Determining the emotional tone behind text — positive, negative, or neutral.
A neural network with billions of parameters trained on massive text corpora to understand and generate human language. Examples: GPT-4, Claude, Gemini, Llama.
A model that has already been trained on a large dataset and can be used as-is or fine-tuned for specific tasks.
Taking a pre-trained model and continuing to train it on a smaller, task-specific dataset to adapt its behavior.
The internal variables of a model that are adjusted during training. More parameters generally mean greater capacity to learn complex patterns.
The process of using a trained model to generate outputs for new inputs (as opposed to training the model).
The numerical values learned during training that determine how input signals are transformed as they pass through the network.
| Acronym | Meaning |
|---|---|
| AI | Artificial Intelligence |
| ML | Machine Learning |
| DL | Deep Learning |
| NLP | Natural Language Processing |
| LLM | Large Language Model |
| RLHF | Reinforcement Learning from Human Feedback |
| RAG | Retrieval-Augmented Generation |
| API | Application Programming Interface |
| SFT | Supervised Fine-Tuning |
| PoC | Proof of Concept |
| GAN | Generative Adversarial Network |
| CNN | Convolutional Neural Network |
| GAN | Generative Adversarial Network |
| AGI | Artificial General Intelligence |
| STT / ASR | Speech-to-Text / Automatic Speech Recognition |
| TTS | Text-to-Speech |