以下內容是我閱讀Probabilistic Graphical Model, Koller 2009一書的讀書筆記，未來將不定期新增內容，此技術屬AI人工智慧範疇。
- Introduction
想要有一個智能體能接收輸入訊息，進而輸出對應動作甚至做Reasoning。但是難道要對每一個專業領域都產出一個智能體嗎？本書將專注於Declarative Representation，其精髓為：The key property of a declarative representation is the separation of knowledge (model) and reasoning (algorithm). The model representation has its own clear semantics, separate from the algorithms that one can apply to it. Thus, we can develop a general suite of algorithms that apply any model within a broad class. Conversely, we can improve our model for a specific application domain without having to modify our reasoning algorithms constantly.
這本書探討的Declarative Representations (or Model-Based Methods)會把Uncertainty納入，而之所以納入Uncertainty的原因乃是：Limitations in our ability to observe the world, limitations in our ability to model it, and possibly even because of innate nondeterminism.
因應上述的Uncertainty，我們需要採用機率理論來描述，亦即：To obtain meaningful conclusions, we need to reason not just about what is possible, but also about what is probable.
