Introducing the CVPR 2018 On-Device Visual Intelligence Challenge

Posted by Bo Chen, Software Engineer and Jeffrey M. Gilbert, Member of Technical Staff, Google Research Over the past year, there have been exciting innovations in the design of deep networks for vision applications on mobile devices, such as the MobileNet model family and integer quantization. Many of these innovations have been driven by performance […]

DeepVariant Accuracy Improvements for Genetic Datatypes

Posted by Pi-Chuan Chang, Software Engineer and Lizzie Dorfman, Technical Program Manager, Google Brain Team Last December we released DeepVariant, a deep learning model that has been trained to analyze genetic sequences and accurately identify the differences, known as variants, that make us all unique. Our initial post focused on how DeepVariant approaches “variant calling” […]

A new video format to reach people across the mobile web and apps

Over the last year, we’ve been working on a way to extend the reach of your video campaigns to people beyond YouTube, especially as they spend more and more time interacting with apps and sites on their mobile devices. Starting today, you can use outstream video ads, a new format built exclusively for mobile environments, […]

Protecting WebView with Safe Browsing

Posted by Nate Fischer, Software Engineer Since 2007, Google Safe Browsing has been protecting users across the web from phishing and malware attacks. It protects over three billion devices from an increasing number of threats, now also including unwanted software across desktop and mobile platforms. Today, we’re announcing that Google Play Protect is bringing Safe […]

An Augmented Reality Microscope for Cancer Detection

Posted by Martin Stumpe, Technical Lead and Craig Mermel, Product Manager, Google Brain Team Applications of deep learning to medical disciplines including ophthalmology, dermatology, radiology, and pathology have recently shown great promise to increase both the accuracy and availability of high-quality healthcare to patients around the world. At Google, we have also published results showing […]

Protegendo nossa rede de anúncios: como funcionam as políticas de publicidade e suas aplicações

Na mês de Março, fizemos um anúncio em nosso blog sobre os esforços do Google para remover anúncios e sites maliciosos de nossas redes. Em 2017, removemos mais de 3.2 bilhões de anúncios (em 2015 foram 700 milhões). São mais de 100 anúncios enganosos por segundo. No geral, usamos uma combinação de pessoas, políticas e […]

Usar a velocidade das páginas na classificação da pesquisa para dispositivos móveis

As pessoas querem ter um acesso rápido às respostas que procuram. Estudos indicam que a velocidade das páginas é uma prioridade para os usuários. Embora esse critério já seja usado na classificação há algum tempo, o uso da velocidade como indicador era concentrado nas pesquisas feitas em computadores. A partir de julho de 2018, a […]

DNS over TLS support in Android P Developer Preview

Posted by Erik Kline, Android software engineer, and Ben Schwartz, Jigsaw software engineer The first step of almost every connection on the internet is a DNS query. A client, such as a smartphone, typically uses a DNS server provided by the Wi-Fi or cellular network. The client asks this DNS server to convert a domain […]

Introducing Semantic Experiences with Talk to Books and Semantris

Posted by Ray Kurzweil, Director of Engineering and Rachel Bernstein, Product Manager, Google Research Natural language understanding has evolved substantially in the past few years, in part due to the development of word vectors that enable algorithms to learn about the relationships between words, based on examples of actual language usage. These vector models map […]