Skip to main content
. Author manuscript; available in PMC: 2022 Jul 27.
Published in final edited form as: Nat Hum Behav. 2022 Jan 27;6(1):111–133. doi: 10.1038/s41562-021-01244-z

Extended Data Figure 2.

Extended Data Figure 2.

Discrete prior distributions used for architecture search. Pooling and convolutional kernel parameters at each layer were uniformly sampled from the lists of values.