The UBC Scientific Software Seminar is inspired by Software Carpentry and its goal is to help students, graduates, fellows and faculty at UBC develop software skills for science.
- What are the learning goals?
- To learn the basics of neural networks and deep learning
- To learn the basics of Keras with Theano (or TensorFlow)
- To train neural networks on GPU servers hosted by AWS
- To meet and collaborate with other students and faculty interested in scientific computing
- What software tools are we going to use?
- Keras: high-level neural networks API
- Theano/TensorFlow: numerical computation on GPUs
- AWS: cloud computing with Amazon Web Services
- SciPy Stack: scientific computing with NumPy, SciPy, matplotlib and pandas
- Python and Jupyter Notebooks
- What scientific topics will we study?
- Neural networks and deep learning following course.fast.ai
- Where do we start? What are the prerequisites?
- UBCS3 Summer 2017 is a continuation of UBCS3 Winter 2017:
- Neural Networks and Deep Learning by Michael Nielsen
- UBCS3 Summer 2017 is a continuation of UBCS3 Winter 2017:
- Who is the target audience?
- Everyone is invited!
- If the outline above is at your level, perfect! Get ready to write a lot of code!
- If the outline above seems too intimidating, come anyway! You'll learn things just by being exposed to new tools and ideas, and meeting new people!
- If you have experience with all the topics outlined above, come anyway! You'll become more of an expert by participating as a helper/instructor!
Please join the mailing list to receive weekly updates about the seminar.
- Week 1 - Tuesday August 1 - 1-3pm - MATH 126
- course.fast.ai
- Getting Started: Setting up AWS
- Lesson 1: Adapt the VGG16 neural network to recognize images of cats and dogs
- Lesson 2: The anatomy of a neural network
- course.fast.ai
- Week 2 - Tuesday August 8 - 1-3pm - MATH 126
- course.fast.ai
- A ddeper look into the architecture of VGG16 using Keras
- course.fast.ai