TERMINOLOGY
AI Fundamentals
- Artificial Intelligence (AI) – The simulation of human intelligence in machines programmed to think and learn like humans.
[#General] [#MachineLearning]
- Machine Learning (ML) – A subset of AI that enables systems to learn and improve from experience without being explicitly programmed.
[#General] [#MachineLearning]
- Deep Learning – A subset of machine learning based on artificial neural networks with multiple layers.
[#MachineLearning] [#NeuralNetworks]
- Neural Network – A computing system inspired by biological neural networks, consisting of interconnected nodes or “neurons.”
[#MachineLearning] [#NeuralNetworks]
- Algorithm – A set of rules or instructions given to an AI, neural network, or computer to help it learn on its own.
[#General] [#MachineLearning]
- Prompt Engineering – The practice of designing and optimizing input prompts to elicit desired outputs from large language models or other AI systems.
[#General] [#NLP]
- Overfitting – A modeling error that occurs when a function is too closely fit to a limited set of data points, potentially reducing its predictive power on new data.
[#MachineLearning]
- Underfitting – A modeling error that occurs when a function is too simple to capture the underlying structure of the data.
[#MachineLearning]
- Hyperparameter – A parameter whose value is set before the learning process begins, distinguishing it from other parameters that are learned during training.
[#MachineLearning]
TERMINOLOGY
Types of Machine Learning
- Supervised Learning – A type of machine learning where the algorithm learns from labeled training data.
[#MachineLearning]
- Unsupervised Learning – A type of machine learning where the algorithm learns patterns from unlabeled data.
[#MachineLearning]
- Reinforcement Learning – A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize a reward.
[#MachineLearning]
- Transfer Learning – A technique where a model developed for one task is reused as the starting point for a model on a second task.
[#MachineLearning]
- Federated Learning – A technique that trains an algorithm across multiple decentralized devices or servers holding local data samples.
[#MachineLearning][#Privacy]
- Semi-supervised Learning – A machine learning approach that combines a small amount of labeled data with a large amount of unlabeled data during training.
[#MachineLearning]
- Online Learning – A method of machine learning where data becomes available in a sequential order and is used to update the model in real-time.
[#MachineLearning]
TERMINOLOGY
Natural Language Processing
- Natural Language Processing – A branch of AI that deals with the interaction between computers and humans using natural language.
[#NLP]
- Sentiment Analysis – The use of NLP techniques to determine the emotional tone behind words.
[#NLP]
- Named Entity Recognition – The process of identifying and classifying key information (entities) in text into predefined categories.
[#NLP]
- Tokenization – The process of breaking down text into smaller units, such as words or sub-words.
[#NLP]
- Word Embedding – A technique of representing words and documents using a dense vector representation.
[#NLP]
- Language Model – A statistical model that calculates the probability of a sequence of words or predicts the next word in a sequence.
[#NLP]
- Part-of-Speech Tagging – The process of marking up words in a text as corresponding to particular parts of speech (e.g., noun, verb, adjective).
[#NLP]
- Lemmatization – The process of reducing words to their base or dictionary form (lemma).
[#NLP]
- Semantic Search – An information retrieval technique that understands the intent and contextual meaning of search queries, rather than just matching keywords.
[#NLP]
- Attention Mechanism – A technique in neural networks that allows the model to focus on specific parts of the input when performing a task, crucial for many NLP applications.
[#NLP]
TERMINOLOGY
Computer Vision
- Computer Vision – A field of AI that trains computers to interpret and understand the visual world.
[#ComputerVision]
- Image Recognition – The ability of AI to identify and detect an object or feature in a digital image or video.
[#ComputerVision]
- Facial Recognition – A technology capable of identifying or verifying a person from a digital image or video frame.
[#ComputerVision]
- Object Detection – A computer vision technique for locating instances of objects in images or videos.
[#ComputerVision]
- Convolutional Neural Network – A class of deep neural networks most commonly applied to analyzing visual imagery.
[#ComputerVision][#NeuralNetwork]
- Semantic Segmentation – A computer vision task where the goal is to partition an image into semantically meaningful parts.
[#ComputerVision]
- YOLO (You Only Look Ince) – A state-of-the-art, real-time object detection system that can detect multiple objects in an image with a single forward pass through a neural network.
[#ComputerVision]
TERMINOLOGY
AI Ethics and Responsible AI
- AI Ethics – The study of moral issues related to the development and use of AI technologies.
[#Ethics]
- Bias in AI – Systematic errors in AI systems that can result in unfair outcomes for certain groups.
[#Ethics]
- Explainable AI (XAI) – AI systems that make decisions or take actions that can be easily understood by humans.
[#Ethics]
- Fairness in AI – The practice of ensuring that AI systems do not discriminate against particular groups or individuals.
[#Ethics]
- AI Governance – The process of defining and implementing rules and best practices for the development and use of AI.
[#Ethics]
- AI Safety – The field focused on ensuring AI systems are designed and operated safely and reliably.
[#Ethics]
- Privacy-Preserving AI – AI techniques that protect individual privacy while still allowing for data analysis and model training.
[#Ethics][#Privacy]
- AI Alignment – The challenge of aligning artificial intelligence systems with human values and intentions.
[#Ethics]
- Algorithmic Transparency – The principle of making the decision-making processes of AI systems understandable and interpretable to humans.
[#Ethics]
TERMINOLOGY
AI Applications
- Chatbot – A computer program designed to simulate human conversation through text or voice interactions.
[#AIApplications][#NLP]
- Recommender System – An AI-based system that suggests items or content to users based on their preferences or behavior.
[#AIApplications][#Media]
- Predictive Analytics – The use of data, statistical algorithms, and machine learning techniques to identify future outcomes based on historical data.
[#AIApplications]
- Customer Segmentation – Using AI to divide a customer base into groups of individuals with similar characteristics.
[#AIApplications][#Marketing]
- Speech Recognition – AI technology that converts spoken language into text.
[#AIApplications][#NLP]
- Autonomous Vehicle – A vehicle capable of sensing its environment and operating without human involvement.
[#AIApplications][#Automobile]
- Predictive Maintainance – The use of AI to predict when equipment is likely to fail so that maintenance can be scheduled proactively.
[#AIApplications][#Production]
- Fraud Detection – The use of AI to identify and prevent fraudulent activities in various sectors, especially finance.
[#AIApplications][#Finance]
- Supply Chain Optimization – Using AI to improve efficiency and reduce costs in supply chain management.
[#AIApplications][#Production]
- Robotic Process Automation (RPA) – The use of AI to automate routine, rule-based digital tasks typically performed by humans.
[#AIApplications][#Automation]
- Digital Twin – A virtual representation of a physical object or system that uses real-time data to enable understanding, learning, and reasoning.
[#AIApplications][#Production]
- Medical Imaging Analysis – AI-powered analysis of medical images for diagnosis and treatment planning.
[#AIApplications][#Healthcare]
- Drug Discovery – The use of AI to accelerate the process of identifying and developing new medications.
[#AIApplications][#Healthcare]
- Personalized Medicine – AI-driven approach to tailor medical treatment to individual patients based on their genetic profile.
[#AIApplications][#Healthcare]
- Remote Patient Monitoring – AI systems that track patient health data outside of traditional healthcare settings.
[#AIApplications][#Healthcare]
- Clinical Decision Support – AI tools that assist healthcare providers in making diagnostic and treatment decisions.
[#AIApplications][#Healthcare]
TERMINOLOGY
Data
- Big Data – Extremely large data sets that may be analyzed computationally to reveal patterns, trends, and associations.
[#DataScience]
- Cloud Computing – The delivery of computing services over the internet, often used to power AI applications.
[#DataScience]
- Edge AI – AI processing that occurs on devices at the edge of the network, rather than in the cloud.
[#DataScience]
- Data Mining – The process of discovering patterns in large data sets involving methods at the intersection of machine learning, statistics, and database systems.
[#DataScience]
- Feature Engineering – The process of using domain knowledge to extract features from raw data to use in machine learning.
[#DataScience][#MachineLearning]
- Data Processing – The technique of transforming raw data into a clean and organized format.
[#DataScience]
- Dimensionality Reduction – The process of reducing the number of random variables under consideration in a dataset.
[#DataScience]
- Data Lake – A centralized repository that allows you to store all your structured and unstructured data at any scale.
[#DataScience][#MachineLearning]
- ETL (Extract, Transform, Load) – A process in data warehousing responsible for pulling data out of one system, processing it, and loading it into another system.
[#DataScience]
TERMINOLOGY
Advanced AI Concepts
- Generative AI – AI systems that can generate new content, such as images, text, or music.
[#AdvancedAI]
- Large Language Models (LLMs) – Advanced AI models trained on vast amounts of text data, capable of understanding and generating human-like text across a wide range of topics and tasks.
[#AdvancedAI][#NLP]
- Transformer – A deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data.
[#AdvancedAI][#NLP]
- Artificial General Intelligence (AGI) – A hypothetical AI that can understand, learn, and apply knowledge across a wide range of tasks at a median human level.
[#AdvancedAI]
- Retrieval Augmented Generation (RAG) – A technique that combines information retrieval with text generation, allowing AI models to access and incorporate external knowledge when generating responses.
[#AdvancedAI][#NLP]
- Knowledge Distillation – A technique for transferring knowledge from a large, complex model (the teacher) to a smaller, simpler model (the student) to improve efficiency while maintaining performance.
[#AdvancedAI][#MachineLearning]
- Transfer Learning – A machine learning method where a model developed for one task is reused as the starting point for a model on a second task.
[#AdvancedAI][#MachineLearning]
- Ensemble Learning – A machine learning technique that combines multiple models to improve overall performance.
[#AdvancedAI][#MachineLearning]
- Adverarial Learning – A technique used in machine learning where two neural networks contest with each other to improve the overall performance.
[#AdvancedAI]
- Quantum Machine Learning – An interdisciplinary field that combines quantum physics with machine learning techniques.
[#AdvancedAI][#MachineLearning]
- Auto ML – The process of automating the end-to-end process of applying machine learning to real-world problems.
[#AdvancedAI][#MachineLearning]
- Federated Learning – A machine learning technique that trains an algorithm across multiple decentralized devices or servers holding local data samples, without exchanging them.
[#AdvancedAI][#Privacy]
- Few-Shot Learning – A type of machine learning where a model is trained to recognize new classes or perform new tasks using only a few examples.
[#AdvancedAI][#MachineLearning]
- Zero-Shot Learning – The ability of AI models to perform tasks or make predictions for classes they haven’t explicitly been trained on, based on descriptive attributes or related information.
[#AdvancedAI][#MachineLearning]
- Neuromorphic Computing – Computing systems that mimic the structure and function of biological neural networks.
[#AdvancedAI][#NeuralNetworks]
- AI Augmentation – The use of AI to enhance human intelligence and capabilities, rather than replace them.
[#AdvancedAI]
- Ensemble Learning – A machine learning paradigm where multiple models are used to solve the same problem and combined to get better results.
[#AdvancedAI][#MachineLearning]
TERMINOLOGY
AI Development and Deployment
- Training Data – The dataset used to train an AI model.
[#AIDevelopment][#DataScience]
- Model – A specific representation of knowledge that has been trained on data and can make predictions.
[#AIDevelopment][#MachineLearning]
- Fine-Tuning – The process of further training a pre-trained model on a specific dataset or task to adapt it for a particular application or domain.
[#AIDevelopment][#MachineLearning]
- Hyperparameter – A parameter whose value is set before the learning process begins, distinguishing it from other parameters that are learned during training.
[#AIDevelopment][#MachineLearning]
- Overfitting – When a model learns the training data too well, including noise and fluctuations, leading to poor performance on new data.
[#AIDevelopment][#MachineLearning]
- Tensorflow -An open-source software library for machine learning and artificial intelligence.
[#AIDevelopment]
- PyTorch -An open-source machine learning library developed by Facebook’s AI Research lab.
[#AIDevelopment]
- Kubernetes – An open-source system for automating deployment, scaling, and management of containerized applications, often used for AI systems.
[#AIDevelopment]
- Jupyter Notebook – An open-source web application that allows data scientists to create and share documents containing live code, equations, and visualizations.
[#AIDevelopment][#DataScience]
- MLOps (Machine Learning Operations) – A set of practices that aims to deploy and maintain machine learning models in production reliably and efficiently.
[#AIDeployment]
- LLMOps (Large Language Model Operations) – A set of practices and tools for managing the lifecycle of large language model applications, including development, deployment, maintenance, and optimization.
[#AIDeployment]
- RAGOps (Retrieval-Augmented Generation Operations) – Operational practices for implementing and maintaining Retrieval-Augmented Generation systems, focusing on integrating information retrieval with text generation in AI applications.
[#AIDeployment]
- AIOps (Artificial Intelligence for IT Operations) – The application of AI, particularly machine learning and data analytics, to enhance and automate IT operations, improving efficiency and effectiveness of IT management.
[#AIDeployment]
- ModelOps (Model Operations) – A framework for governing and managing the lifecycle of decision models, including AI and machine learning models, focusing on operationalization across various platforms.
[#AIDeployment]
- DataOps (Data Operations) – An automated, process-oriented methodology used by data teams to improve the quality and reduce the cycle time of data analytics, combining agile development, DevOps, and statistical process control.
[#AIDeployment][#DataScience]
- API (Application Programming Interface) – A set of protocols and tools for building software applications, often used to integrate AI capabilities into other systems.
[#AIDevelopment][#AIDeployment]
- Docker – A platform used to develop, ship, and run applications in containers, providing consistency across different environments.
[#AIDeployment]
- CI/CD (Continuous Integration/Continuous Deployment) – A method to frequently deliver apps to customers by introducing automation into the stages of app development.
[#AIDeployment]
- A/B Testing – A method of comparing two versions of a machine learning model or application to determine which one performs better.
[#AIDevelopment][#AIApplications]
- Model Versioning – The practice of tracking changes to machine learning models over time, similar to version control in software development.
[#AIDevelopment]
- AI Observability – The ability to measure, track, and understand AI system outputs, including model performance, data quality, and operational metrics, to ensure reliability and trustworthiness.
[#AIDevelopment]