This paper focuses on continual meta-learning, where few-shot tasks are heterogeneous
and sequentially available. Recent works use a mixture model for meta-knowledge to deal …

Although neural networks have seen tremendous success as predictive models in a variety
of domains, they can be overly confident in their predictions on out-of-distribution (OOD) …

In large deep neural networks that seem to perform surprisingly well on many tasks, we also
observe a few failures related to accuracy, social biases, and alignment with human values …

Discrete variational auto-encoders (VAEs) are able to represent semantic latent spaces in
generative learning. In many real-life settings, the discrete latent space consists of high …

SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input
vector onto a probability simplex and reweights the input by concentrating the probability …

Neural network models have become ubiquitous in the machine learning literature. These
models are compositions of differentiable building blocks that compute dense …

This paper focuses on continual meta-learning, where few-shot tasks are sequentially
available and sampled from a non-stationary distribution. Motivated by this challenging …

Softmax with the cross entropy loss is the standard configuration for current neural text
classification models. The gold score for a target class is supposed to be 1, but it is never …