Model
One word, taught differently in 4 fields. Each use is given apart.
In Systems & CS
A system of abstractions that presents selected parts of reality in order to solve specific problems.
In AI & ML
A representation of an MDP parameterized by that estimates the transition probabilities and reward function of the environment.
In Medicine
Representations that are essentially wrong, but can still be useful if understood for their limitations.
In Physics
An idea that sorts out confusing information and explains the most important features of a phenomenon.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Transition probability2Abstraction1Environment dynamics1MDP1Propositional symbols1Reinforcement learning1Reward function1Scientific method1
Opens up
Concepts that name this one as a prerequisite.
In Systems & CS
2Each in their own terms, from the easiest level.
Brian Yu
An assignment of a truth value to every propositional symbol, representing a possible world.
In AI & ML
1David Silver
In Medicine
1In Physics
1Lectures that assume it
9- Uninformed Search
- Learning: Near Misses and Felicity Conditions in AI
- Inference Methods for Deep Learning
- Machine Learning: Naive Bayes
- Some Set Theory of Kaufmann Models
- Determinacy Strength with Universally Baire Sets
- Property Based Testing: The Past, The Present, and The Future
- Minimal Models and Beta-Categoricity
- Seafood: Understanding and Protecting a Precious Natural Resource
Connections
22The lectures that define it or assume it, and the concepts next to it.
Concepts7
Show 1 moreShow fewer
Lectures15
- Introduction to Reinforcement Learning
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- The Atom (The Mechanical Universe, Episode 49)
- Integrating Learning and Planning
- Models Beyond Diagrams: Conceptualizing Software Models
- Critical thinking in Clinical Medicine
Show 9 moreShow fewer
- Uninformed Search
- Learning: Near Misses and Felicity Conditions in AI
- Inference Methods for Deep Learning
- Machine Learning: Naive Bayes
- Some Set Theory of Kaufmann Models
- Determinacy Strength with Universally Baire Sets
- Property Based Testing: The Past, The Present, and The Future
- Minimal Models and Beta-Categoricity
- Seafood: Understanding and Protecting a Precious Natural Resource