Through model-based learning, students use diagrams as a way to think about and reason with systems—and to think about how complex systems interact and change.
“Model-based learning” seems like a reframing of classic teaching practices, but it’s nonetheless a powerful reframing. Emphasizing the model—and encourage students to test and iterate their models—is catchy. It’s also deliberately organizational—it requires students to organize and structure their thinking about a given system, often visually.
At AI SF, Danny Lange presented how to train puppies: “On the road to artificial general intelligence” — game simulations Unity3D plus reinforcement learning used to train virtual puppies to play “fetch” and other skills. Building on this, Danny described several forms of learning inspired by biology, which go beyond deep learning. He showed examples of virtual puppies for:
Imitation Learning: e.g., see https://bit.ly/2zvYH51 (start 0:15)
Curriculum Learning: start with an easy problem, then make learning challenges progressively harder
Curiosity-driven Exploration: gets beyond problems which random exploration would never reach, i.e., agents don’t get stuck in a room (saddle points) because they want to explore other rooms
”In universities, this requires a rebalancing from the current emphasis on research to teaching. (A dean at one of Ontario’s more highly ranked universities told me recently that virtually every day there is a request to grant teaching release to a professor, yet no one has ever asked for release from research.)” — http://blog-en.heqco.ca/2017/07/harvey-p-weingarten-the-evolution-of-learning-outcomes-now-comes-the-exciting-part/
Fede_Von Hacker News (e.g., not a catch-all big-data-will-save-the-world thing).