7.5 Expert Systems

Expert systems capture a human expert's knowledge as rules so a computer can give expert-style advice.

Chapter 7: Major Areas of AI

An expert system was one of the first big commercial AI successes, especially in the 1970s and 80s. It has two main parts: a knowledge base (facts and IF-THEN rules from experts) and an inference engine (the logic that applies the rules to a new case).

A famous early one, MYCIN (1970s), suggested treatments for blood infections and in tests performed comparably to some specialists.

They're transparent - you can trace exactly why it gave its answer - but hard to maintain and can't learn by themselves. Today they're often combined with machine learning.

Key takeaways

Knowledge base + inference engine

Early commercial AI success (e.g. MYCIN)

Explainable, but can't learn on its own

We make AI make sense.
Life on the timeline.
Learn it properly.
AI for GenZs.
1.1 What Is Artificial Intelligence (AI)?
1.2 Definition and Meaning of AI
1.3 History and Evolution of AI
1.4 Goals and Objectives of AI
1.5 Importance of AI in Today's World
1.6 Real-World Applications of AI
1.7 Advantages and Limitations of AI
2.1 Narrow AI (Weak AI)
2.2 General AI (Strong AI)
2.3 Superintelligent AI
2.4 Reactive Machines
2.5 Limited Memory AI
2.6 Theory of Mind and Self-Aware AI
3.1 How AI Works
3.2 Data, Algorithms, and Models
3.3 AI vs. Human Intelligence
3.4 AI vs. Machine Learning vs. Deep Learning
3.5 Rule-Based Systems
3.6 Intelligent Agents and Environments
4.1 What Is Machine Learning?
4.2 How Machine Learning Works
4.3 Supervised Learning
4.4 Unsupervised Learning
4.5 Reinforcement Learning
4.6 Training Data and Testing Data
4.7 Model Training and Evaluation
5.1 What Is Deep Learning?
5.2 Introduction to Neural Networks
5.3 Artificial Neurons and Layers
5.4 How Neural Networks Learn
5.5 Deep Neural Networks
5.6 Applications of Deep Learning
6.1 What Is Generative AI?
6.2 How Generative AI Works
6.3 Large Language Models (LLMs)
6.4 ChatGPT and AI Assistants
6.5 AI Image, Audio, and Video Generation
6.6 Prompt Engineering Basics
6.7 Benefits and Limitations of Generative AI
7.1 Natural Language Processing (NLP)
7.2 Computer Vision
7.3 Speech Recognition
7.4 Robotics
7.5 Expert Systems
7.6 Planning and Decision-Making
7.7 Recommendation Systems
8.1 What Is Data in AI?
8.2 Structured and Unstructured Data
8.3 Data Collection and Preparation
8.4 Introduction to Algorithms
8.5 Classification and Regression
8.6 Clustering
8.7 Model Accuracy and Performance
9.1 Introduction to Python for AI
9.2 NumPy and Pandas
9.3 Matplotlib for Data Visualization
9.4 Scikit-learn
9.5 TensorFlow and PyTorch
9.6 AI APIs and Online Platforms
9.7 No-Code and Low-Code AI Tools
10.1 AI in Education
10.2 AI in Healthcare
10.3 AI in Business and Finance
10.4 AI in Agriculture
10.5 AI in Manufacturing
10.6 AI in Transportation
10.7 AI in Cybersecurity
10.8 AI in Daily Life
11.1 AI Bias and Fairness
11.2 Data Privacy and Security
11.3 Hallucinations and Incorrect Outputs
11.4 Transparency and Explainability
11.5 Job Automation and Employment
11.6 Responsible AI
11.7 AI Safety and Governance
12.1 Emerging AI Trends
12.2 AI Agents and Automation
12.3 Human–AI Collaboration
12.4 Opportunities and Career Paths in AI
12.5 Skills Required to Learn AI
12.6 The Future of AI
What is a transformer, actually?
Prompting: from beginner to dangerous
How diffusion models paint from noise
RAG, agents, and other buzzwords decoded
Build your first AI workflow
Why octopuses might dream in color
Tested, so you don't have to.
Say hello.
Privacy policy.
Cookie policy.
Terms and conditions.