Twitter | Search | |
Tweets Jul 18
What if bounding boxes could be more precise than just University of Toronto and achieved state-of-the-art accuracy in boundary detection with their new approach called STEAL. Read the paper:
Reply Retweet Like Jul 17
There are a lot of factors to consider when deploying ML applications. Which are you most comfortable with?
Reply Retweet Like Jul 16
Improve your neural network performance using initialization, L2 and dropout regularization, Batch normalization, and gradient checking. Enroll now in the Deep Learning Specialization:
Reply Retweet Like Jul 15
Reply Retweet Like Jul 11
Should video chat use AI to make your face look more engaged? FaceTime can warp the image of your face so people you chat with will think you're looking them in the eye. You can see the subtle warp from the straw as it passes over the eyes:
Reply Retweet Like Jul 10
"A machine capable of learning? That sounds wonderful." Learn how heroes of deep learning and first became interested in AI:
Reply Retweet Like Jul 9
From parsing text data to spouting original poetry, walk through each step of building a text generator in TensorFlow with . Enroll in the Specialization:
Reply Retweet Like Jul 8
Ladies, if he: - requires lots of supervision - yet always wants more power - can't explain decisions - optimizes for the average outcome - dismisses problems as edge cases - forgets things catastrophically He's not your man, he's a deep neural network. Creds:
Reply Retweet Like Jul 4
Happy 4th of July from the team!
Reply Retweet Like Jul 3
Even the heroes of deep learning had to start somewhere! Hear how and Andrej first entered the world of AI:
Reply Retweet Like Jul 2
Say cheese! Build a visual sentiment analysis system to detect how happy someone is based on facial expression. Get started creating applications from the ground up in the Deep Learning Specialization:
Reply Retweet Like Jul 1
When 's DL-generated tweets are wiser than most humans
Reply Retweet Like Jun 27
NLP models are getting better at comprehension tasks like question answering and sentiment analysis. Check out XLNet, a new pre-training algorithm from and , which builds on and outperforms BERT:
Reply Retweet Like Jun 26
"Nvidia has more software engineers than hardware engineers. A GPU is a lot more than just a chip. It gets good performance through amazing compilers, libraries, frameworks, and applications.” Learn more about Bryan Catanzaro ’s work at :
Reply Retweet Like Jun 25
YOLOv2 is one of the most effective object detection algorithms out there. Learn how to use it to detect cars and other objects in the Deep Learning Specialization:
Reply Retweet Like Jun 24
It's a never-ending cycle
Reply Retweet Like Jun 21
Deep learners: What have you learned or applied from Course 1 and 2 of the TensorFlow Specialization? Let us know in the comments!
Reply Retweet Like Jun 21
Want more SensorFlow fun from ? Enroll in the TensorFlow Specialization now on :
Reply Retweet Like Jun 20
Course 3 of the TensorFlow Specialization is now available on Coursera! You’ll learn how to build natural language processing systems using TensorFlow. Enroll in the Specialization for $49/month or audit for free:
Reply Retweet Like Jun 19
Course 3 is less than 24 hours away! Andrew and Laurence introduce Shakespearean text generation, the main NLP application you’ll build in the course:
Reply Retweet Like