Multithreaded predictions with TensorFlow Estimators

Caching estimators to speed up inference by >100x

TensorFlow Estimators provide a set of mid-level APIs for writing, training, and using machine learning models, with a focus on…

Tricking a Machine into Thinking You’re Milla Jovovich

And other types of adversarial attacks in machine learning

Neural autoregressive flows

An expressive and tractable framework for learning probabilistic models

Women in Machine Learning: Negar Rostamzadeh

There aren’t enough women in tech. Since the 1980s the number of women completing…

Modern recipes for anomaly detection

A quick tour of anomaly detection as I try to find Golden…

Securing machine learning models against adversarial attacks

What are adversarial defences?

NIPS’17 highlights and trends overview

The emergence of Deep Learning 2.0 and the return of Bayes