Demonstrates that providing explantions and model criticism can be useful tools to improve the reliability of ImageNet-trained CNNs for end-users.
Provides evidence that human experimentation in physical environments is effective at revealing properties of interest, and learning from observations relies on the learning goals.
Reviews recent work that analyzes the egocentric view of infants, highlighting the connection between the data and internal machinery for statistical learning.
Adversarial examples trained on an ensemble of CNNs with a retinal preprocessing layer reduce the accuracy of time-limited humans in a two alternative forced choice task.
Computer vision models trained on data obtained from head-mounted cameras on children performs better than data from adults.
Applies curriculum learning to a RL context to achieve policies.