Artificial Intelligence (AI): Intelligence displayed by machines, performing tasks like human intelligence.
Example: Siri and Alexa use AI to understand and respond to voice commands.

Machine Learning (ML): Teaching computers to learn from data without explicit programming.
Tools: TensorFlow, Scikit-learn.

Deep Learning (DL): A subfield of ML using deep neural networks to learn complex patterns.
Example: DeepFace by Facebook for facial recognition.

Neural Networks: Algorithm modelled on the human brain’s structure.
Tools: Keras, PyTorch.

Natural Language Processing (NLP): Teaching machines to understand human language.
Example: Google Translate.

Prompt Engineering: To guide AI by asking it specific questions or giving instructions. Think of it like giving a smart robot clear directions on what you want it to do.
Tools: ChatGPT, Midjourney.

Data Processing: Preparing raw data for machine learning, including cleaning and transforming.
Tools: Pandas, Apache Spark.

Generative Adversarial Network (GAN): Creating new things by training two neural networks against each other.
Example: DeepArt for generating art.

Reinforcement Learning: Learning by trial and error, receiving rewards or punishments.
Tools: OpenAI Gym, RLlib.

Graphics Processing Unit (GPU): Special computer chip for complex calculations, often used in AI.
Example: NVIDIA’s GPUs for deep learning.

Supervised Learning: Machine learning with labelled training data.
Tools: SVM, Random Forest.

Compute Unified Device Architecture (CUDA): Technology for solving complex problems by breaking them into smaller pieces.
Example: Used in NVIDIA GPUs for parallel computing.

Feature Engineering: Selecting and creating features to improve machine learning.
Tools: Featuretools, scikit-learn.

Generative Art: Art created using algorithms, often involving randomness. Example: Processing for creating visual art.

Large Language Model (LLM): Machine learning model trained on vast text data.
Example: OpenAI’s GPT models.

Unsupervised Learning: Machine learning without labelled training data.
Tools: k-Means, Hierarchical Clustering.

Overfitting: Model performs well on training data but poorly on new data.
Example: A complex polynomial fit that fails on new data.

Embedding: Numerical representation of words capturing their meaning.
Tools: Word2Vec, GloVe.

Generative Pre-trained Transformer (GPT): Large language model by OpenAI.
Example: GPT-3 for text generation.

Spatial Computing: Adding digital information to the physical world.
Example: Augmented reality apps like Pokémon GO.

Webhook: Sending messages or data between programs in real-time.
Tools: Zapier, Integromat.