In this session we'll dive into the journey that Google chooses to take in order focus on AI: what was the mindset, what were the challenges and what is the direction for the future.
12. Not so fast...
CC-BY-SA-2.5 Wikimedia Commons https://commons.wikimedia.org/wiki/File:Komondor_Westminster_Dog_Show_crop.jpg
CC-BY-2.0 Wikimedia Commons https://commons.wikimedia.org/wiki/File:2014_Westminster_Kennel_Club_Dog_Show_(12487315865).jpg
CC-BY-2.0 Petful https://www.flickr.com/photos/petsadviser-pix/16395099127
CC-BY-SA-2.0 Jeffrey Beall https://www.flickr.com/photos/denverjeffrey/6903790333
13.
14. How Can You Get Started with Machine Learning?
• Three ways, with varying complexity:
• Use a Cloud-based or Mobile API (Vision,
Natural Language, etc.)
• Use an existing model architecture, and retrain
it or fine tune on your dataset
• Develop your own machine learning models for
new problems
Moreflexible,butmoreeffortrequired
15.
16. In case you were wondering...
CC-BY-SA-2.5 Wikimedia Commons https://commons.wikimedia.org/wiki/File:Komondor_Westminster_Dog_Show_crop.jpg
CC-BY-2.0 Wikimedia Commons https://commons.wikimedia.org/wiki/File:2014_Westminster_Kennel_Club_Dog_Show_(12487315865).jpg
CC-BY-2.0 Petful https://www.flickr.com/photos/petsadviser-pix/16395099127
CC-BY-SA-2.0 Jeffrey Beall https://www.flickr.com/photos/denverjeffrey/6903790333
17. What is TensorFlow
• Open source Machine Learning library
• Especially useful for Deep Learning
• For research and production
• Apache 2.0 license
21. You mentioned Deep Learning? What ?!
• The first question to answer: What’s a Neural Network ?
• Inspired by Biology:
• Two flavors: Supervised an Unsupervised
24. What happened in the last decade…
• Algorithms: This area has seen some improvements, but most of the early
wins came from fairly old ideas. Now that Deep Learning is showing success
we are seeing some good advances as well.
• Datasets: Training large networks is hard without large enough datasets.
MNIST can only go so far in pushing the limits. Having datasets like ImageNet
has really helped pushed the state of the art in vision.
• Compute: the biggest game changer in recent years.