Tag: Neural Networks

Faster Neural Networks Straight from JPEG

Uber AI Labs introduces a method for making neural networks that process images faster and more accurately by leveraging JPEG representations.

Forecasting at Uber: An Introduction

In this article, we provide a general overview of how our teams leverage forecasting to build better products and maintain the health of the Uber marketplace.

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

As powerful and widespread as convolutional neural networks are in deep learning, AI Labs’ latest research reveals both an underappreciated failing and a simple fix.

M4 Forecasting Competition: Introducing a New Hybrid ES-RNN Model

With a solid margin, Uber senior data scientist Slawek Smyl won the M4 Competition with his hybrid Exponential Smoothing-Recurrent Neural Networks (ES-RNN) forecasting method.

Measuring the Intrinsic Dimension of Objective Landscapes

Curious about what it is like to traverse the high-dimensional loss landscapes of modern neural networks? Check out Uber AI Labs’ latest research on measuring intrinsic dimension to find out.

SBNet: Leveraging Activation Block Sparsity for Speeding up Convolutional Neural Networks

Uber ATG Toronto developed Sparse Blocks Network (SBNet), an open source algorithm for TensorFlow, to speed up inference of our 3D vehicle detection systems while lowering computational costs.

Year in Review: 2017 Highlights from the Uber Engineering Blog

To ring in the New Year, the Uber Engineering Blog shares some of our editor's picks for 2017.

Engineering More Reliable Transportation with Machine Learning and AI at Uber

In this article, we highlight how Uber leverages machine learning and artificial intelligence to tackle engineering challenges at scale.

Engineering Uncertainty Estimation in Neural Networks for Time Series Prediction at Uber

Uber Engineering introduces a new Bayesian neural network architecture that more accurately forecasts time series predictions and uncertainty estimations.

Engineering Extreme Event Forecasting at Uber with Recurrent Neural Networks

Recurrent neural networks equip Uber Engineering's new forecasting model to more accurately predict rider demand during extreme events.

Popular Articles