2287 results for "earn" across all locations
New app features and data show how Uber can improve safety on the road
We believe that technologies like Uber provide an incredible opportunity to improve road safety in new and innovative ways—before, during and after every ride. Today, we’re excited to announce several new safety pilots to improve rider and driver safety.
Efficient Multiple Instance Metric Learning Using Weakly Supervised Data
M. T. Law, Y. Yu, R. Urtasun, R. S. Zemel, E. P. Xing
We consider learning a distance metric in a weakly supervised setting where “bags” (or sets) of instances are labeled with “bags” of labels. A general approach is to formulate the problem as a Multiple Instance Learning (MIL) problem where the metric is learned so that the distances between instances inferred to be similar are smaller than the distances between instances inferred to be dissimilar. […] [PDF]
Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
F. Such, V. Madhavan, E. Conti, J. Lehman, K. Stanley, J. Clune
Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on challenging deep reinforcement learning (RL) problems. […] [PDF]
Deep RL @ NeurIPS 2018
Incremental Few-Shot Learning with Attention Attractor Networks
M. Ren, R. Liao, E. Fetaya, R. Zemel
This paper addresses this problem, incremental few- shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the overall classification performance on both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Networks, which regularizes the learning of novel classes. [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
Y. Wu, M. Ren, R. Liao, R. Grosse
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is unrolled. […] [PDF]
International Conference on Learning Representations (ICLR), 2018
Remote vs. in-person work: 3 benefits of returning to the office
After more than a year of working remotely, learn why business models that include working in an office can benefit employees.
Connect and parcel deliveries pilots
Learn about how you can help move things from A to B with parcel deliveries.
‘Give yourself some grace’ — advice for balancing work and life from a mother and Program Manager
Learn about Elle’s career, motherhood and how she grapples with the challenges she encounters.
Meet Joe Shone, Head of Enterprise Product Sales for Uber Freight
Meet Joe, learn about the early days of Uber Freight, and what drives him nearly 5 years on.
Top Tips to Smash Holiday Sales
Read these insights and top tips to learn how your restaurant can capture more sales this holiday season.