Artificial Intelligence (AI)
The field of computer science focused on creating systems capable of intelligent behavior, including learning, reasoning, and problem-solving.
Machine Learning (ML)
A subset of AI that enables systems to learn from data and improve performance without being explicitly programmed.
Cognitive Computing
A field of AI that aims to mimic human thought processes for problem-solving and decision-making.
Deep Learning
A specialized branch of machine learning using multi-layered neural networks to model complex patterns in large datasets.
Neural Network
A computing model inspired by biological neurons, used for tasks such as image recognition and natural language processing.
Transformer Model
A deep learning architecture used in NLP, such as BERT and GPT, known for its attention mechanisms that process words in context.
Self-Attention Mechanism
A component in Transformer models that allows the model to weigh the importance of different words in a sequence.
Graph Neural Networks (GNNs)
A type of neural network designed to process data structured as graphs, used in applications like recommendation systems and fraud detection.
Supervised Learning
A type of machine learning where models are trained on labeled data to make predictions.
Unsupervised Learning
A machine learning method that identifies patterns and structures in data without labeled examples.
Reinforcement Learning (RL)
A machine learning approach where an agent learns optimal behavior by interacting with an environment and receiving rewards.
Few-Shot Learning
An AI capability where a model learns a new task with very few training examples.
Zero-Shot Learning
An AI model’s ability to perform a task without being explicitly trained on specific examples of that task.
Natural Language Processing (NLP)
A field of AI focused on enabling machines to understand, interpret, and generate human language.
Large Language Model (LLM)
A deep learning model trained on massive amounts of text data, capable of generating human-like language.
Tokenization
The process of breaking text into individual components such as words, phrases, or subwords for NLP tasks.
Retrieval-Augmented Generation (RAG)
A hybrid AI approach that combines information retrieval from external sources with generative models to produce more accurate responses.
Embeddings
Numerical vector representations of words, sentences, or data points used for similarity calculations in AI applications.
Embedding Space
A high-dimensional space where data points (e.g., words, images) are represented as numerical vectors to capture semantic similarities.
Semantic Search
An AI-powered search method that understands the meaning behind queries rather than relying on exact keyword matches.
Finetuning
The process of adapting a pre-trained AI model to a specific task by training it on a smaller, domain-specific dataset.
Knowledge Distillation
A technique where a smaller model learns from a larger, pre-trained model to achieve similar performance with fewer resources.
Model Drift
The degradation of an AI model’s performance over time due to changing data distributions.
Explainable AI
Techniques used to make AI model decisions more transparent and interpretable.
Model Deployment
The process of integrating a trained AI model into a production environment where it can make real-world predictions.
Cloud Deployment
The deployment of AI models on cloud infrastructure (e.g., AWS, Google Cloud, Azure) to ensure scalability, accessibility, and remote processing.
On-Premises Deployment
The deployment of AI models within an organization’s own data centers, offering greater control over security and data privacy.
Hybrid Deployment
A deployment strategy that combines both cloud and on-prem solutions, allowing flexibility between private and public AI processing.
Edge Deployment
The deployment of AI models directly on edge devices (e.g., IoT devices, mobile phones, embedded systems) for real-time, low-latency processing.
Serverless AI
An AI deployment model where models are hosted in a serverless environment, running only when needed and scaling automatically.
Containerized Deployment
A deployment method that uses containerization (e.g., Docker, Kubernetes) to package AI models with dependencies for portability and scalability.
MLOps
A set of practices combining machine learning, DevOps, and data engineering to efficiently deploy, monitor, and manage AI models.
Model Monitoring
The practice of tracking an AI model's performance in production to detect issues such as model drift, latency, and accuracy degradation.
Inference Pipeline
A structured process for handling real-time AI predictions, including data pre-processing, model execution, and result post-processing.
Batch Processing
A deployment approach where AI models process large volumes of data at scheduled intervals rather than in real-time.
Real-Time AI
AI models that process and analyze data instantly to generate immediate insights or predictions.
GPU Acceleration
The use of Graphics Processing Units (GPUs) to accelerate deep learning training and inference processes, improving AI performance.
Agent
An AI-driven entity that perceives its environment, makes decisions, and takes actions to achieve goals.
Multi-Agent System
A system where multiple AI agents interact, collaborate, or compete to achieve objectives.
Autonomous System
A self-governing AI system capable of making decisions without human intervention.
Swarm Intelligence
A decentralized AI approach inspired by natural systems like ant colonies, where simple agents collaborate to solve complex problems.
Prompt Engineering
The practice of designing and refining input prompts to optimize AI-generated responses.
User Prompt
The input provided by a user to an AI system, guiding its response generation, commonly seen in chatbots and language models.
System Prompt
A predefined instruction given to an AI model by developers or applications to guide its behavior and tone before processing user input.
Bias in AI
Systematic errors in AI models due to biased training data or design choices, leading to unfair or skewed outcomes.
Ethical AI
The study and implementation of AI systems that align with ethical principles such as fairness, accountability, and transparency.
Hallucination
When an AI model generates false or misleading information that is not based on factual data.
