News

Real Time Facial Expression Recognition

Computer animated agents and robots bring new dimension in human computer interaction which makes it vital as how computers can affect our social life in day-to-day activities. Face to face communication is a real-time process operating at a time scale in the order of milliseconds. The level of uncertainty at this time scale is considerable, making it necessary for humans and machines to rely on sensory rich perceptual primitives rather than slow symbolic inference processes.

How we spent two weeks hunting an NFS bug in the Linux kernel

Meet TiDB: An open source NewSQL database

TiDB is an open source NewSQL database released under the Apache 2.0 License. Because it speaks the MySQL protocol, your existing applications will be able to connect to it using any MySQL connector, and most SQL functionality remains identical (joins, subqueries, transactions, etc.). Step under the covers, however, and thereare differences.

How plants evolved to make ants their servants

Plants are boring. They just sit there photosynthesizing while animals have all the fun. Right?

Accurate Online Speaker Diarization with Supervised Learning

Speaker diarization, the process of partitioning an audio stream with multiple people into homogeneous segments associated with each individual, is an important part of speech recognition systems. By solving the problem of “who spoke when”, speaker diarization has applications in many important scenarios, such as understanding medical conversations, video captioning and more. However, training these systems with supervised learning methods is challenging — unlike standard supervised classification tasks, a robust diarization model requires the ability to associate new individuals with distinct speech segments that weren’t involved in training.

The next version of HTTP won’t be using TCP

Today’s HTTP (versions 1.0, 1.1, and 2) are all layered on top of TCP (Transmission Control Protocol). TCP, defined as part of the core set of IP (Internet Protocol) layers, provides reliable, ordered, and error-checked delivery of data over an IP network. ‘Reliable’ means that if some data goes missing during transfer (due to a hardware failure, congestion, or a timeout), the receiving end can detect this and demand that the sending end re-send the missing data; ‘ordered’ means that data is received in the order that it was transmitted in; ‘error-checked’ means that any corruption during transmission can be detected.

A Google Brain engineer’s guide to entering AI

Note that this guide was written in November 2018 to complement an in-depth conversation on the 80,000 Hours Podcast with Catherine Olsson and Daniel Ziegler on how to transition from computer science and software engineering in general into ML engineering, with a focus on alignment and safety. If you like this guide, we’d strongly encourage you to check out the podcast episode where we discuss some of the instructions here, and other relevant advice. Technical AI safety is a multifaceted area of research, with many sub-questions in areas such as reward learning, robustness, and interpretability.

Introspected REST: An Alternative to REST and GraphQL

In this manifesto, we will give a specific definition of what REST is, according to Roy, and see the majority of APIs and API specs (JSONAPI, HAL etc) fail to follow this model. We will see what problems a RESTful API brings and why API designers have been constantly avoiding using it but instead come up with half-way solutions or retreat to alternative models like RPC-over-HTTP or, lately, GraphQL. Then, we will propose a new model, Introspected REST, that solves the issues that REST creates and allows the design of progressively evolvable APIs, in a much simpler way than conventional REST.

How to Develop Convolutional Neural Network Models for Time Series Forecasting

Orange Skin, Thick Bones, and All the Other Ways the Human Body Could Change on Mars