Advancing the state of the art

As Big Data has altered the face of research, the same factors of Volume, Velocity and Variety used to define it, are changing the opportunities of analytic data exploration as well; thus, the introduction of the term Big Analytics. Improvement in algorithms and computing power provide the foundation to produce automated platforms that can identify patterns in analytic model results beyond...

The recent years have seen an explosive growth in web and mobile application development. Such applications typically have rapid development cycles, expect mobile-friendly features and serverless characteristics such as rapid deployment (with minimal provisioning) capabilities, scalability to handle workload spikes, and convenient pay-as-you-go billing. Google’s Firestore is a NoSQL serverless...

Video streaming services are among the largest web applications in production, and a large source of downstream internet traffic. A large-scale video streaming service at Google, YouTube, leverages a Content Delivery Network (CDN) to serve its users. A key consideration in providing a seamless service is cache efficiency. In this work, we demonstrate machine learning techniques to improve the...

Inspired by biological and cultural evolution, there have been many attempts to explore and elucidate the necessary conditions for open-endedness in artificial intelligence and artificial life. Using a continuous cellular automata called Lenia as the base system, we built large-scale evolutionary simulations using parallel computing framework JAX, in order to achieve the goal of never-ending...

Background Photographs of the external eye were recently shown to reveal signs of diabetic retinal disease and elevated glycated haemoglobin. This study aimed to test the hypothesis that external eye photographs contain information about additional systemic medical conditions. Methods We developed a deep learning system (DLS) that takes external eye photographs as input and predicts systemic...

Text reading order is a crucial aspect in the output of an OCR engine, with a large impact on downstream tasks. Its difficulty lies in the large variation of domain specific layout structures, and is further exacerbated by real-world image degradations such as perspective distortions. We propose a lightweight, scalable and generalizable approach to identify text reading order with a multi-...

We present a method to separate speech signals from noisy environments in the embedding space of a neural audio codec. We introduce a new training procedure that allows our model to produce structured encodings of audio waveforms given by embedding vectors, where one part of the embedding vector represents the speech signal, and the rest represent the environment. We achieve this by...

Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised Machine Translation, or UNMT. However, these models still struggle in a variety of ways, including aspects of translation that for a human are the easiest---for instance, correctly...

Recent work in visual end-to-end learning for robotics has shown the promise of imitation learning across a variety of tasks. However, such approaches are often expensive and require vast amounts of real world training demonstrations. Additionally, they rely on a time-consuming evaluation process for identifying the best model to deploy in the real world. These challenges can be mitigated by...