How Uber Uses ResNet

The article discusses Uber's participation in the NeurIPS 2019 conference, highlighting their commitment to advancing machine learning through research and practical applications.

The article introduces Loss Change Allocation (LCA), a method for gaining insights into the neural network training process by measuring how changes in loss are allocated to individual parameters.

Ludwig v0. 2 introduces significant enhancements to its deep learning toolbox, including new features such as Comet.

The article discusses the creation of an Atari model zoo aimed at enhancing the understanding of deep reinforcement learning (deep RL).

The article discusses an innovative approach to enhance the performance of Convolutional Neural Networks (CNNs) by utilizing JPEG's internal representations.

The article discusses Peloton, Uber's unified resource scheduler designed to manage diverse cluster workloads efficiently.

The article discusses the limitations of Convolutional Neural Networks (CNNs) in performing coordinate transformations and introduces the CoordConv layer as a solution.

The article discusses Uber's innovative hybrid Exponential Smoothing-Recurrent Neural Network (ES-RNN) model that won the M4 Forecasting Competition.

The article discusses SBNet, an open-source algorithm developed by Uber ATG that leverages activation block sparsity to enhance the speed of Convolutional Neural Networks (CNNs).