Recent efforts at explaining the interplay of memorization and generaliz...
The aim of object-centric vision is to construct an explicit representat...
Recent works demonstrate that early layers in a neural network contain u...
Recent research in clustering face embeddings has found that unsupervise...
Individuals are often faced with temptations that can lead them astray f...
Transfer-learning methods aim to improve performance in a data-scarce ta...
Real world learning scenarios involve a nonstationary distribution of cl...
Discovering causal structures from data is a challenging inference probl...
Optimal decision making requires that classifiers produce uncertainty
es...
Recent work has argued that classification losses utilizing softmax
cros...
A discriminatively trained neural net classifier achieves optimal perfor...
Although deep feedforward neural networks share some characteristics wit...
Building reliable machine learning systems requires that we correctly
un...
Deep-learning vision models have shown intriguing similarities and
diffe...
We aim to bridge the gap between typical human and machine-learning
envi...
Human learners appreciate that some facts demand memorization whereas ot...
Supervised deep-embedding methods project inputs of a domain to a
repres...
In human perception and cognition, the fundamental operation that brains...
We explore the behavior of a standard convolutional neural net in a sett...
Machine learning promises methods that generalize well from finite label...
We consider visual domains in which a class label specifies the content ...
Learning long-term dependencies in extended temporal sequences requires
...
The focus in machine learning has branched beyond training classifiers o...
Recurrent neural networks (RNNs) are difficult to train on sequence
proc...
Deep-embedding methods aim to discover representations of a domain that ...
We investigate recurrent neural network architectures for event-sequence...
Advances in machine learning have produced systems that attain human-lev...
In theoretical cognitive science, there is a tension between highly
stru...