How Spotify Uses Artificial Intelligence, Big Data, and Machine Learning

Despite the hate it gets from musicians over the less-than-ideal music streaming rates, Spotify is here to stay. Hundreds of millions of people around the world use Spotify to listen to their music, and its unsurprising to see why. With an impressive catalog of over 50 million songs and podcast episodes (and 40,000 new ones being uploaded per day), the Swedish company shows no signs of slowing down.

Perpetual View Generation of Natural Scenes from a Single Image

We introduce the problem of perpetual view generation—long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which work for a limited range of viewpoints and quickly degenerate when presented with a large camera motion.

Arguing Machines: Human Supervision of Black Box AI Systems

We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task. We show that disagreement between the two systems, without any knowledge of underlying system design or operation, is sufficient to arbitrarily improve the accuracy of the overall decision pipeline given human supervision over disagreements.

Level Up: Mastering statistics with Python

Investigate a dataset with summary statistics and some basic data visualizations using the Python libraries NumPy, pandas, matplotlib, and Seaborn.

Deep Generative Modelling: A Comparative Review

Deep generative modelling is a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which making trade-offs including run-time, diversity, and architectural restrictions. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. These techniques are drawn under a single cohesive framework, comparing and contrasting to explain the premises behind each, while reviewing current state-of-the-art advances and implementations.