Workshop – Hands-On Deep Learning in the Cloud: Fast and Lean Data Science with Tensorflow, Keras, and TPUs
Thursday, June 20, 2019 in Las Vegas
Full day: 8:30am – 4:30pm
Intended Audience: Anyone who wishes to learn how to create deep learning systems using TensorFlow, Keras, and Google Cloud.
Knowledge Level: Level: Basic knowledge of machine learning terminology. Minimal programming experience with a C-family language such as Python, C/C++, C# or Java is recommended but not required. Some deep learning experience is welcome but do not worry if don’t remember exactly what the cross-entropy is. Fundamental concepts will be re-explained as we build, train, tune and deploy several models together, using Tensorflow/Keras and Google Cloud.
Laptop requirements. Attendees must bring their own laptop for use during this hands-on workshop. Instructions for pre-workshop software download and installation will be provided to registrants one week before the workshop.
Other deep learning workshop: This is one of two full-day workshops on deep learning held at Mega-PAW. These two workshops are complementary – you can opt to take either one alone, or both. Neither is a prerequisite for the other. The other workshop is Deep Learning in Practice: A Hands-On Introduction.
Training deep learning models used to be a game of patience. Training runs took hours and you needed hundreds of them to tune a model. Well, at least, it gave researchers the time to read new ML papers…
Today, as software engineers add machine learning to their skill sets, they need to work faster because they have products to ship. Making use of the cloud is a big component of that, since it provides nearly unlimited compute resources, but introduces costs that you need to keep an eye on. After all, to leverage the full-scale potential of deep convolutional neural networks, it takes a full-scale solution – for both model training and deployment.
Large-Scale Image Classification
To provide specific hands-on experience, this workshop focuses on image classification applications – culminating with a large-scale problem on real data – by way of convolutional neural networks, which are the most common form of advanced deep learning applied to larger-scale image classification problems.
During this workshop, you will gain hands-on experience training deep learning on Google’s TPUs (Tensor Processing Units).
In-house Google expert and renowned lecturer Martin Gorner will show you the full potential of convolutional neural nets and TPU – without a Ph.D. This workshop will bring you through the full deep learning journey, from the data to the model architecture and model tuning, all the way to deploying models in production.
You will learn to leverage Google Cloud and related tools. With a focus on not wasting time and money, TPUs train faster and at a lower cost. Google’s Colaboratory offers free GPUs and TPUs, as well as notebook sharing and collaboration. And Google’s Machine Learning Engine allows you to run trainings overnight, in parallel, on powerful clusters.
During this workshop day, attendees will gain the following practical hands-on experience:
- Practical steps to deploy TensorFlow and Keras within Google Cloud.
- High-level TensorFlow code using Keras, layers and Datasets.
- Engineering tips, tricks and best practices to build and train neural networks that solve your problems.
- Convolutional neural network architectures for image processing. Convnet basics, convolution filters and how to stack them. Learnings from the Inception model: modules with parallel convolutions, 1x1 convolutions. A simple modern convnet architecture: Squeezenet. Convenets for detection: the YOLO (You Only Look Once) architecture.
- Full-scale model training and serving with Tensorflow’s Keras APIs on Google Cloud ML Engine and Cloud TPUs.
- The application of convolutional neural network training across a real, challenging image classification data set – which will take only minutes to train thanks to the use of TPUs.
- Workshop starts at 8:30am
- Morning Coffee Break at 10:30am – 11:00am
- Lunch provided at 12:30pm – 1:15pm
- Afternoon Coffee Break at 3:00pm – 3:30pm
- End of the Workshop: 4:30pm
Coffee breaks and lunch are included.
Martin Görner, Developer Relations, Google
Martin Görner works in developer relations at Google, where he focuses on parallel processing and machine learning. Passionate about science, technology, coding, algorithms, and everything in between, Martin’s first role was in the Computer Architecture Group at STMicroelectronics. He also spent 11 years shaping the nascent ebook market, starting at Mobipocket, which later became the software part of the Amazon Kindle and its mobile variants. He holds a degree from Mines Paris Tech. He is best known today for the “Tensorflow without a PhD” series.