Automating the Art of Data Augmentation

Part III Theory

As we have seen in the previous blog post, data augmentation techniques have achieved remarkable gains when applied to neural network models. In this blog post, we reflect on the success story of various augmentation techniques and review our recent work that study theoretical properties of data augmentation. [Read More]

Automating the Art of Data Augmentation

Part II Practical Methods

Instead of performing manual search, automated data augmentation approaches hold promise to search for more powerful parameterizations and compositions of transformations. Perhaps the biggest difficulty with automating data augmentation is how to search over the space of transformations. This can be prohibitively expensive due to the large number of transformation... [Read More]

Automating the Art of Data Augmentation

Part I Overview

Data augmentation is a de facto technique used in nearly every state-of-the-art model in applications such as image and text classification. Heuristic data augmentation schemes are often tuned manually by human experts with extensive domain knowledge, and may result in suboptimal augmentation policies. In this blog post, we provide a... [Read More]

Into the Wild: Machine Learning In Non-Euclidean Spaces

Is our comfortable and familiar Euclidean space and its linear structure always the right place for machine learning? Recent research argues otherwise: it is not always needed and sometimes harmful, as demonstrated by a wave of exciting work. Starting with the notion of hyperbolic representations for hierarchical data two years... [Read More]