Ai_ml terms
ML Types
Supervised (labelled examples), unsupervised (find patterns), reinforcement learning (reward signals), and self-supervised (model creates its own labels).
3mo ago
ai_ml intermediate
Neural Networks — Conceptual Overview
Layers of connected neurons transforming input to output through learned weights — the foundation of deep learning and modern LLMs.
3mo ago
ai_ml intermediate
AI Hallucination
9
When an LLM generates confident, plausible-sounding text that is factually incorrect — a fundamental property of next-token prediction, not a bug to be patched away.
3mo ago
ai_ml intermediate
Embeddings
Dense numerical vector representations of text, images, or other data — capturing semantic meaning so that similar items have similar vectors and can be found via distance search.
3mo ago
ai_ml intermediate
Large Language Models (LLMs)
2
Neural network models trained on vast text corpora that can generate, summarise, translate, and reason about text — the technology behind ChatGPT, Claude, and Gemini.
3mo ago
ai_ml intermediate
Prompt Engineering
1
The practice of designing and iterating on LLM input prompts to reliably produce accurate, useful, and appropriately formatted outputs.
3mo ago
ai_ml intermediate
Using AI APIs in PHP
PHP 8.0+
1
Integrating LLM APIs (OpenAI, Anthropic, Gemini) into PHP applications — for text generation, classification, extraction, and embedding-based search.
3mo ago
ai_ml intermediate
Vector Databases
Databases specialised for storing and querying high-dimensional vectors — enabling fast approximate nearest-neighbour search across millions of embeddings.
3mo ago
ai_ml intermediate