Profile cover photo
Profile photo
Yili Zhao
104 followers
104 followers
About
Posts

Post has shared content
Check out this project that uses deep learning to beat the state of the art for cardiac segmentation, implements a new type of network architecture, and has a well structured GitHub repo.
Add a comment...

Post has shared content
Nice walk-through by Harshvardhan Gupta in a great scientific paper «A simple neural network module for relational reasoning» from Google's DeepMind.
Add a comment...

Post has shared content
Vehicle Detection with Dlib 19.5
Dlib v19.5 is out and there are a lot of new features . There is a dlib to caffe converter, a bunch of new deep learning layer types, cuDNN v6 and v7 support, and a bunch of optimizations that make things run faster in different situations, like ARM NEON su...
Add a comment...

Post has shared content
On the application of DL to scientific research. Applying deep learning (thanks to CNNs / ConvNets and transfer learning) to discover new plant species in herbarium data. Herbariums are large collections (often millions) of plant specimens created and maintained for a large variety of scientific research.
Add a comment...

Post has shared content
Add a comment...

Post has shared content
To explore how ML can learn subjective concepts, we introduce an experimental deep-learning system for artistic content creation that uses Street View panoramas to create professional-level photos. Check out some of the results, below!
Add a comment...

Post has shared content
As researchers, we have always wondered: if we scale up the amount of training data for computer vision deep learning models by 10x, will the accuracy double? How about 100x or maybe even 300x? Will the accuracy plateau or will we continue to see increasing gains with more and more data? We explore this on the Research blog as we Revisit the Unreasonable Effectiveness of Data.
Add a comment...

Post has shared content
Qt 5.9 is 100% awesome! Find everything you need to know about Qt 5.9 LTS here: http://hubs.ly/H07YfPR0
Photo
Add a comment...

Post has shared content
Today, we are happy to release Tensor2Tensor (T2T), an open-source system for training deep learning models in TensorFlow. T2T facilitates the creation of state-of-the art models for a wide variety of ML applications, such as translation, parsing, image captioning and more, enabling the exploration of various ideas much faster than previously possible.
Add a comment...

Post has shared content
Wait while more posts are being loaded