AI News, Discussing TensorFlow History, Challenges, and Learning Perspective
- On Wednesday, September 26, 2018
- By Read More
Discussing TensorFlow History, Challenges, and Learning Perspective
TensorFlow is an open-source machine learning library originally developed by Google.
This session with Yaroslav Bulatov and Lukasz Kaiser of the Google Brain team overviews the formation of TensorFlow in brief, provides some examples of the tool applied within Google products, plans for the future, etc.
(OpenAI is a non-profit artificial intelligence research organization founded by recognized machine learning/AI research engineers and scientists.) He highlighted the following aspects:
- On Monday, September 23, 2019
MarI/O - Machine Learning for Video Games
MarI/O is a program made of neural networks and genetic algorithms that kicks butt at Super Mario World. Source Code: "NEAT" ..
Computer Vision and Machine Learning, by Nick Wong
A basic introduction to some fundamental concepts in machine learning using Tensorflow, coupled with an introduction to OpenCV2, a computer vision project.
Heroes of Deep Learning: Andrew Ng interviews Andrej Karpathy
Lesson 2: Practical Deep Learning for Coders
CONVOLUTIONAL NEURAL NETWORKS For last week's assignment your goal was to get into the top 50% of the Kaggle Dogs v Cats competition. This week ...
Combining crowd and AI to scale professional-quality translation
With more and more non-English content on the web and the growing need for companies to talk in their customers' languages, can NMT alone do the job?
The Halite Global AI Programming Competition in Google Cloud (Cloud Next '18)
Halite is an open source artificial intelligence programming competition, created by Two Sigma, where players build bots using the coding language of their ...
Continuously Train & Deploy Spark ML and Tensorflow AI Models from Jupyter Notebook to Production
Towards Machines that Perceive and Communicate
Kevin Murphy (Google Research) Abstract: In this talk, I summarize some recent work in my group related to visual scene understanding and "grounded" ...
Transforming Your Business with Cloud TPUs (Cloud Next '18)
Cloud TPUs are hardware accelerators for machine learning (ML) that enable ML engineers, ML researchers, and data science teams to iterate quickly and ...
Lecture 18: Tackling the Limits of Deep Learning for NLP
Lecture 18 looks at tackling the limits of deep learning for NLP followed by a few presentations.