Vanilla Neural Network

Recent work showed that models for multilingual machine translation can increase the number of languages they translate by scraping the web for pairs of equivalent sentences in different languages. A new study radically expanded the language repertoire through training on untranslated web text.

DeepMind’s AlphaGo famously dominated Go, a game in which players can see the state of play at all times. A new AI system demonstrated similar mastery of bridge, in which crucial information remains hidden.

Most U.S. state agencies use AI without limits or oversight. An investigative report probed reasons why efforts to rein them in have made little headway. Since 2018, nearly every proposed bill aimed at studying or controlling how state agencies use automated decision systems.

Want to become an AI practitioner? Here’s a program that will take you from beginner to job-ready. You may already have a head start, depending on your background. For a motivated person who starts with a solid high-school education it may take around two years.

Amazon reported long-term success using machine learning to shrink its environmental footprint. The online retailer developed a system that fuses product descriptions, images, and structured data to decide how an item should be packed for shipping.

Deep learning can predict how patients will respond to two antidepressant medicines.

New research shows that drastically increasing the number of layers in a graph neural networks improves its performance on large datasets.

A new machine learning method aims to improve a machine’s ability to determine and locate points of interest.

Playing a team sport involves a fluid blend of individual and group skills. Researchers integrated both types of action into realistic humanoid agents that play football (known as soccer in the U.S.).

The paper that introduced the transformer famously declared, “Attention is all you need.” To the contrary, new work shows you may not need transformer-style attention at all.What’s new: Hanxiao Liu and colleagues at Google

Self-attention enables transformer networks to track relationships between distant tokens — such as text characters — in long sequences, but the computational resources required grow quadratically with input size.

The activation function known as ReLU builds complex nonlinear functions across layers of a neural network, making functions that outline flat faces and sharp edges. But how much of the world breaks down into perfect polyhedra?

Why use a complex model when a simple one will do? New work shows that the simplest multilayer neural network, with a small twist, can perform some tasks as well as today’s most sophisticated architectures.

Researchers have used neural networks to generate novel views of a 3D scene based on existing pictures plus the positions and angles of the cameras that took them. In practice, though, you may not know the precise camera

Ideally, real-time 3D applications such as virtual and augmented reality transition smoothly between different viewpoints of a scene — but generating a fresh perspective can take time. New research speeds the process.