AI Taxonomy

AI Taxonomy - by Mohd Yamani Idna Idris

An overview of the different fields and concepts within Artificial Intelligence.

AI Hierarchy

• Artificial Intelligence (AI)
  • Machine Learning (ML)
    • Supervised Learning
    • Unsupervised Learning
    • Reinforcement Learning
    • Deep Learning
      • Generative AI
        • Transformer
          • Large Language Model (LLM)
  • Rule-Based Systems

Machine Learning (ML)

A field of AI where systems learn from data to make predictions or decisions without being explicitly programmed. ML is often considered the foundation of modern AI.

Supervised Learning

Models learn from labeled training data, where the desired output is already known.

• Examples: Linear Regression, Logistic Regression, Support Vector Machines (SVM), Decision Trees.
• Use Cases: Spam classification in email, predicting house prices, image classification.

Unsupervised Learning

Models discover patterns and structures in unlabeled data without a known output.

• Examples: K-Means Clustering, Principal Component Analysis (PCA).
• Use Cases: Customer segmentation, fraud detection, social network analysis.

Reinforcement Learning

An agent learns to make decisions by receiving rewards for good actions and penalties for bad ones.

• Examples: Q-Learning, Deep Q-Networks (DQN).
• Use Cases: AI for playing games (e.g., AlphaGo), robotics, optimizing resource management.

Deep Learning

A subset of Machine Learning that uses artificial neural networks with multiple layers to model high-level abstractions in data.

• Examples: Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs).
• Use Cases: Image and video recognition, natural language processing (NLP), speech recognition.

Generative AI

Models that can generate new and original content, such as text, images, music, or code.

• Examples: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs).
• Use Cases: Creating realistic art and images, text generation, designing new molecules.

Rule-Based Systems

AI systems that use a predefined set of "if-then" rules to reason and make decisions. They do not learn from data.

• Examples: Expert Systems, decision trees with hard-coded logic.
• Use Cases: Simple chatbots, medical diagnosis systems, tax filing software.

Transformer

A powerful neural network architecture, central to many modern AI models, that uses a mechanism called "attention" to weigh the importance of different parts of the input data.

• Examples: GPT (Generative Pre-trained Transformer), BERT (Bidirectional Encoder Representations from Transformers).
• Use Cases: Machine translation, text summarization, question answering.

Large Language Model (LLM)

A type of Transformer model trained on a massive amount of text data to understand and generate human-like language.

• Examples: GPT-4, Gemini, Claude.
• Use Cases: Conversational AI (chatbots), content creation, code generation, creative writing.