ObjectDetection's profile picture. #computerVision #objectDetection #machineLearning #deepLearning
http://fb.com/objectdetection

Object Detection

@ObjectDetection

#computerVision #objectDetection #machineLearning #deepLearning http://fb.com/objectdetection

“Using Tensorflow Object Detection to do Pixel Wise Classification” by Priya Dwivedi towardsdatascience.com/using-tensorfl…


“Machine Learning Top 10 Open Source Projects (v.Mar 2018)” by @Mybridge medium.mybridge.co/machine-learni…


Object Detection 已轉發

Divers came to the rescue of a Whale Shark who became tangled in a net. The Whale Shark made its appreciation known. 💙💚

來自 The Dodo

“Understanding Learning Rates and How It Improves Performance in Deep Learning” by @ikanez towardsdatascience.com/understanding-…


Object Detection 已轉發

My team open sourced #FHIR (Fast Healthcare Interoperability Resources) protocol buffers today. It allows #EHR data to be handled in a portable way research.googleblog.com/2018/03/making…


“Google’s new AI knows which images you’ll like — before you’ve even seen them” by @wef medium.com/world-economic…


Machine Learning Explained: Understanding Supervised, Unsupervis on Data Science Central: datasciencecentral.com/profiles/blogs…


Object Detection 已轉發

Private training data can easily be extracted from the predictions of a trained model. Your user data (health data, private information) isn't safe by default. The good news? Adding just a little randomness can fully eliminate the memorization effect.

Turns out it's possible to recreate training data from a NN using only black box api access--no need for params. Upshot for medical researchers and vendors is that if you train on unanonymized patient records, your model is PHI. arxiv.org/abs/1802.08232

alexbrattmd's tweet image. Turns out it's possible to recreate training data from a NN using only black box api access--no need for params. Upshot for medical researchers and vendors is that if you train on unanonymized patient records, your model is PHI.

arxiv.org/abs/1802.08232


Object Detection 已轉發

Meta-learning lets you tune hyperparameters with SGD! When @jonLorraine9 told me this, I thought it was too good to be true. The catch is you need large hypernetworks, but you can mostly avoid that by jointly training the hypernet and hyperparams: arxiv.org/abs/1802.09419

DavidDuvenaud's tweet image. Meta-learning lets you tune hyperparameters with SGD!  When @jonLorraine9 told me this, I thought it was too good to be true.  The catch is you need large hypernetworks, but you can mostly avoid that by jointly training the hypernet and hyperparams: arxiv.org/abs/1802.09419

“Chinese Startups Hauled In Half of 2017 Global AI Funding” by @Synced_Global medium.com/@Synced/chines…


Object Detection 已轉發

Do you want to learn about AI+Healthcare? Our @Stanford team is releasing a new Medium publication to share exciting work across the field! Check it out: medium.com/stanford-ai-fo…


Object Detection 已轉發

Announcing the AI Fund! We have raised $175 million, and will start multiple new businesses that use AI to improve human life. We also hope to help many of you enter AI, and do the important work of building an AI-powered society. medium.com/@andrewng/anno…

AndrewYNg's tweet image. Announcing the AI Fund! We have raised $175 million, and will start multiple new businesses that use AI to improve human life. We also hope to help many of you enter AI, and do the important work of building an AI-powered society. medium.com/@andrewng/anno…

Loading...

Something went wrong.


Something went wrong.