en
0.25
0.5
0.75
1.25
1.5
1.75
2
How to Grow a Mind: Statistics, Structure and Abstraction
Published on Aug 17, 201237237 Views
The fields of cognitive science and artificial intelligence grew up together, with the twin goals of understanding human minds and making machines smarter in more humanlike ways. Yet since the 1980s t
Related categories
Chapter list
How to grow a mind: statistics, structure and abstraction00:00
Acknowledgments00:16
The goal01:26
A success story: AI Technologies “statistics on a grand scale” (1)03:11
A success story: AI Technologies “statistics on a grand scale” (2)05:01
The big question (1)05:58
The big question (2)06:25
Learning from very few examples06:26
The big question (3)08:14
Common-sense understanding (1)09:38
Common-sense understanding (2)10:23
Common-sense understanding (3)11:21
Common-sense understanding (4)13:30
The approach: statistics meets knowledge (1)14:31
The approach: statistics meets knowledge (2)15:24
Is probability even an appropriate basis for modeling cognition?19:12
Basic cognitive capacities as intuitive Bayesian statistics20:53
Everyday prediction problems21:07
Graphs22:06
Scaling up to the hard problems24:23
Probabilistic graphical models (e.g., Bayes nets)24:54
Towards probabilistic programs (1)26:09
Towards probabilistic programs (2)29:46
Towards probabilistic programs (3)31:58
Towards probabilistic programs (4)32:27
Probabilistic programming languages (1)33:20
Probabilistic programming languages (2)34:17
Precursors: The mid-20th century view of minds as machines (1)34:51
Precursors: The mid-20th century view of minds as machines (2)35:38
Precursors: The mid-20th century view of minds as machines (3)36:07
Precursors: The mid-20th century view of minds as machines (4)36:19
Precursors: Theory construction as probabilistic program induction36:34
Learning from very few examples (1)36:37
Learning from very few examples (2)37:02
Learning from very few examples (3)37:15
Learning from very few examples (4)38:16
Discovering the structural form of a domain38:30
Causal learning and reasoning (1)41:34
Causal learning and reasoning (2)42:38
Causal learning and reasoning (3)44:21
Intuitive physics: stability45:35
Example (1)46:06
Example (2)46:16
Example (3)46:18
Example (4)46:22
Example (5)46:25
Example (6)46:25
Modeling stability judgments (1)46:39
Modeling stability judgments (2)46:52
Modeling stability judgments (3)47:31
Modeling stability judgments (4)47:51
Modeling stability judgments (5)48:45
Physical simulation, or visual/geometric heuristic?50:14
The flexibility of common sense51:01
Physical simulation, or visual/geometric heuristic?51:53
Direction and distance of fall51:58
Mass-sensitive predictions52:25
Learning dynamical parameters53:10
Table (1)53:13
Table (2)53:25
Table (3)53:27
Table (4)53:29
Table (5)53:30
Table (6)53:33
Table (7)53:35
Table (8)53:38
If you bump the table… (1)53:48
If you bump the table… (2)54:04
Varying objects, constraints, forces54:26
Intuitive psychology (1)55:29
Intuitive psychology (2)55:30
Goal inference as inverse probabilistic planning55:45
Theory of mind: Joint inferences about beliefs and preferences58:55
Social goals, moral evaluation59:51
Pragmatic inference in language (1)01:00:48
Pragmatic inference in language (2)01:00:52
Intuitive psychology as inverse decision-making/planning01:01:03
Frontiers01:01:08
Conclusions01:08:25