Are you new to deep learning and want to learn how to use it in your work? Deep learning can achieve state-of-the-art accuracy in many human-like tasks such as naming objects in a scene or recognizing optimal paths in an environment. Please join us for a MathWorks Seminar and Workshop on Deep Learning using MATLAB, sponsored by CAEN.
Registration is required to attend. Please register at: www.mathworks.com/umich
Session 1 (Seminar) – Demystifying Deep Learning: A Practical Approach in MATLAB
When: Tuesday, March 13, 3:00 p.m. – 5:00 p.m.
Where: Duderstadt Center 3336 (Advanced Training Lab 1)
In this seminar, we’ll demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. In doing so, we’ll decipher practical knowledge of the domain of deep learning. We’ll build and train neural networks that recognize handwriting, classify food in a scene, and figure out the drivable area in a city environment.
Along the way, you’ll see MATLAB features that make it easy to:
- Manage extremely large sets of images
- Visualize networks and gain insight into the black box nature of deep networks
- Perform classification and pixel-level semantic segmentation on images
- Import training data sets from networks such as GoogLeNet and ResNet
- Import and use pre-trained models from TensorFlow and Caffe
- Speed up network training with parallel computing on a cluster
- Automate manual effort required to label ground truth
- Automatically convert a model to CUDA to run on GPUs
Session 2 (Workshop) – Practical Applications of Deep Learning – A Hands-On MATLAB Workshop
When: Tuesday, March 13, 6:00 p.m. – 9:00 p.m.
Where: Bob & Betty Beyster Building 1670
Deep learning achieves human-like accuracy for many tasks considered algorithmically unsolvable with traditional machine learning. It is frequently used to develop applications such as face recognition, automated driving, and image classification.
In this hands-on workshop, you will write code and use MATLAB to:
- Learn the fundamentals of deep learning and understand terms like “layers”, “networks”, and “loss”
- Build a deep network that can classify your own handwritten digits
- Access and explore various pre-trained models
- Use transfer learning to build a network that classifies different types of food
- Train deep learning networks on GPUs in the cloud
- Learn how to use GPU code generation technology to accelerate inference performance
Anyone can register for the seminar, but if you plan on attending the workshop, the seminar is a prerequisite.