Transparent Computers: Designing Understandable Intelligent Systems

Computers today can be very opaque. When they make a mistake, it's hard to understand why, and it's hard to fix the problem. Computers should instead be transparent. They should be able to reason like people and explain their reasoning to people. This book discusses techniques for designing and building transparent computers ranging from declarative methods to neural networks. It describes ways of implementing dialogue, explanation, and learning in transparent computers.