This class is intended for people who want to better understand to use tensorflow to solve their computational supervised and unsupervised problems. Tensorflow is the dominant programming language for exploring AI and RL problems. Tensorflow is supported by Google and a large open source community.
AI and RL techniques have been recently deployed in optimizing supervised network hyperparameters, solving games, economic models and multidimensional real world problems. We will be using recently published papers to develop an intuition on how to program them in tensorflow and modify them to your specific problem domain.
Agenda
- Basics Numpy, Scipy and math operations using Tensorflow
- Constructing convolutional neural networks for visual learning
- Language and Temporal Learning
- Tensorflow Debuggers
- Tensorflow Profiler
- Transfer Learning across architectures
- Reinforcement learning and control
Intended Audience
Programmers, managers, investors, enthusiast pretty much anyone technically curious about deploying artificial intelligence. If you are familiar with supervised learning but did not know how to implement them in tensorflow.
What do I need to know to be successful:
All you need is curiosity in the subject and access to a laptop for which you have administrator access. (Specifically so you can turn off firewall protection in case you have issues connecting to the cloud). We will grant you access to a google cloud server with a connected GPU for conducting the hands-on exercise.
About 35% of the class is lectures and 65% is hands on programming. In order to do the hands-on programming segment you need to know python.
A general understanding of numpy, scipy and tensorflow will help. But since people have varying experience with these topics, we will be providing a quick overview.
info@leftbrain.consulting