What is a deterministic?
A system that always returns the same output for a given input.
deterministic explained in plain English
A system that always returns the same output for a given input. For example, the ReLU function is deterministic because: - When the input is negative, the output is always 0. - When the input is nonnegative, the output always equals the input. By contrast, a function that returns a random number each time it is called is nondeterministic. Deterministic systems are generally much easier to test than nondeterministic systems. LLMs are usually nondeterministic; that is, the LLM's response to the same prompt often differs.
Example
Practitioners refer to deterministic when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- average precision at k
A metric for summarizing a model's performance on a single prompt that generates ranked results, such as a numbered list of book recommendations.
- black box model
A model whose "reasoning" is impossible or difficult for humans to understand.
- Chain-of-Thought Prompting
Asking an AI to show its reasoning step by step before giving a final answer, which often improves accuracy on complex tasks.
- conversational coding
An iterative dialog between you and a generative AI model for the purpose of creating software.
- direct prompting
Synonym for zero-shot prompting.
- distillation
The process of reducing the size of one model (known as the teacher) into a smaller model (known as the student) that emulates the original model's predictions as faithfully as possible.
- emergent behavior
An LLM's ability to generate responses for prompts that it was not explicitly trained on.
- factuality
Within the ML world, a property describing a model whose output is based on reality.
- few-shot learning
A machine learning approach, often used for object classification, designed to train effective classification models from only a small number of training examples.
- few-shot prompting
A prompt that contains more than one (a "few") example demonstrating how the large language model should respond.