Publications

Squeeze-and-Excitation Networks

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial a...

Comprehensive molecular portraits of human breast tumours

A Practical Guide to Splines

Efficient Estimation of Word Representations in Vector Space

We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in ...

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we conside...

Planetary boundaries: Guiding human development on a changing planet

Crossing the boundaries in global sustainability The planetary boundary (PB) concept, introduced in 2009, aimed to define the environmental limits within which humanity can safe...

The Core Competence of the Corporation

SciPy 1.0: fundamental algorithms for scientific computing in Python.

Structure, function and diversity of the healthy human microbiome

Studies of the human microbiome have revealed that even healthy individuals differ remarkably in the microbes that occupy habitats such as the gut, skin and vagina. Much of this...

The expression of the emotions in man and animals.

Acknowledgments List of Illustrations Figures Plates Preface to the Anniversary Edition by Paul Ekman Preface to the Third Edition by Paul Ekman Preface to the Second Edition by...

Activating Mutations in the Epidermal Growth Factor Receptor Underlying Responsiveness of Non–Small-Cell Lung Cancer to Gefitinib

A subgroup of patients with non-small-cell lung cancer have specific mutations in the EGFR gene, which correlate with clinical responsiveness to the tyrosine kinase inhibitor ge...

Aggregated Residual Transformations for Deep Neural Networks

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transfor...