recentpopularlog in


« earlier   
ageitgey/face_recognition: The world's simplest facial recognition api for Python and the command line
The world's simplest facial recognition api for Python and the command line - ageitgey/face_recognition
python  machinelearning  facedetection 
1 minute ago by rona25
TensorFlow Course
Simple and ready-to-use tutorials for TensorFlow.
Not built by Google.
20 hours ago by adamtait
How to deliver on Machine Learning projects
Great tips from experience building ML software.
20 hours ago by adamtait
Introduction to Machine Learning for Coders
By Jeremy Howard, formerly Kaggle.
Based on UCSF course.
Built to succeed Andrew Ng's course with modern tools.
20 hours ago by adamtait
deepmind/trfl: TensorFlow Reinforcement Learning
TensorFlow Reinforcement Learning. Contribute to deepmind/trfl development by creating an account on GitHub.
tensorflow  machinelearning 
23 hours ago by derekharmel
Is It Possible to Know Too Much About Basketball? - The Ringer
Augmented graphics existed before CourtVision. The NFL has used yellow first-down markers for three decades, and MLB has featured strike zones for nearly as long. But those graphics focus on numbers such as speed, distance, and location. Second Spectrum is using computers to process information that is far more illustrative of performance. “What we wanted to do required a machine to understand the game like a coach or a human, then augment it,” Maheswaran said. “John Madden taught us a lot about football, and, because of the breaks in the game, he drew a lot on the screen. We want to bring the same thing to basketball.”
basketball  machinelearning 
yesterday by gwijthoff
[1810.01993] Exascale Deep Learning for Climate Analytics
We extract pixel-level masks of extreme weather patterns using variants of Tiramisu and DeepLabv3+ neural networks. We describe improvements to the software frameworks, input pipeline, and the network training algorithms necessary to efficiently scale deep learning on the Piz Daint and Summit systems. The Tiramisu network scales to 5300 P100 GPUs with a sustained throughput of 21.0 PF/s and parallel efficiency of 79.0%. DeepLabv3+ scales up to 27360 V100 GPUs with a sustained throughput of 325.8 PF/s and a parallel efficiency of 90.7% in single precision. By taking advantage of the FP16 Tensor Cores, a half-precision version of the DeepLabv3+ network achieves a peak and sustained throughput of 1.13 EF/s and 999.0 PF/s respectively.
machinelearning  DeepLearning 
yesterday by researchknowledge
[D] ML is losing some of its luster for me. How do you like your ML career? : MachineLearning
Soliciting thoughts on ML careers (in industry or academia), especially in light of machine learning and deep learning hype. I work as an applied...
jobs  machinelearning 
yesterday by colindocherty

Copy this bookmark:

to read