AI Vocabulary
| Term | Description |
|---|---|
| AI Ethics | Study and application of moral principles concerning AI systems, including fairness, transparency, accountability. |
| Artificial Intelligence (AI) | The simulation of human intelligence processes by machines, including learning, problem-solving, and decision-making. |
| Bias in AI | Systematic errors in AI models or algorithms resulting in unfair outcomes. |
| Computer Vision | AI field enabling computers to interpret and understand the visual world through digital images or videos. |
| Deep Learning | Subset of ML using neural networks with many layers to learn complex patterns from data. |
| Explainable AI (XAI) | Ability to provide transparent, interpretable explanations of AI model predictions and decisions. |
| Generative Adversarial Networks (GANs) | ML frameworks where two networks are trained together to produce realistic outputs. |
| Large Language Model (LLM) | Advanced AI models trained on vast amounts of text data to understand and generate human-like text. |
| Machine Learning (ML) | Subset of AI enabling systems to learn and improve from experience without being explicitly programmed. |
| Natural Language Processing (NLP) | AI branch enabling computers to understand, interpret, and generate human language. |
| Neural Networks | Computational models inspired by the human brain's structure, composed of interconnected nodes (neurons). |
| Reinforcement Learning | ML type where an agent learns to make decisions to maximize cumulative reward. |
| Semi-supervised Learning | Learning paradigm combining labeled and unlabeled data to improve accuracy. |
| Supervised Learning | ML type where the model is trained on labeled data, learning to make predictions based on input-output pairs. |
| Transfer Learning | ML technique where a model trained on one task is repurposed for a second related task. |
| Unsupervised Learning | ML type where the model finds hidden patterns in unlabeled data. |
Source: ChatGPT3.5