Extrapolation–the ability to make inferences that go beyond the scope of one's experiences–
is a hallmark of human intelligence. By contrast, the generalization exhibited by …

Machine learning systems, especially with overparameterized deep neural networks, can
generalize to novel test instances drawn from the same distribution as the training data …

Invariances to translations have imbued convolutional neural networks with powerful
generalization properties. However, we often do not know a priori what invariances are …

We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of
the Neural Process family that models translation equivariance in the data. Translation …

Neural networks are surprisingly good at interpolating and perform remarkably well when
the training set examples resemble those in the test set. However, they are often unable to …

Tremendous progress has been made in visual representation learning, notably with the
recent success of self-supervised contrastive learning methods. Supervised contrastive …

Dataset augmentation, the practice of applying a wide array of domain-specific
transformations to synthetically expand a training set, is a standard tool in supervised …

A representation is supposed universal if it encodes any element of the visual world (eg,
objects, scenes) in any configuration (eg, scale, context). While not expecting pure universal …

Learning effective visual representations that generalize well without human supervision is a
fundamental problem in order to apply Machine Learning to a wide variety of tasks …

An important component for generalization in machine learning is to uncover underlying
latent factors of variation as well as the mechanism through which each factor acts in the …