Using Transfer Learning | Deep Learning for Engineers, Part 4

This video introduces the idea of transfer learning. Transfer learning is modifying an existing deep network architecture and then retraining it to accomplish your task rather than the task it was original trained for. In this video, we walk through how transfer learning was used to develop a network that could recognize high five motions in acceleration data.

Check out these other resources:
• MATLAB Deep learning examples: https://bit.ly/DL-examples
• 5 Reasons to use MATLAB for deep learning: https://bit.ly/2QlbNNc
• Getting Started with Deep Network Designer: https://bit.ly/2Qof12l
• Classify Time Series Using Wavelet Analysis and Deep Learning: https://bit.ly/3deq6wb
• Pretrained Deep Neural Networks: https://bit.ly/2QgC7rQ

Note: Starting with R2024a, importing data and training the network is no longer part of the Deep Network Designer App. This functionality is now done using the MATLAB function trainnet. Learn more: https://bit.ly/trainnet

--------------------------------------------------------------------------------------------------------
Get a free product trial: https://goo.gl/ZHFb5u
Learn more about MATLAB: https://goo.gl/8QV7ZZ
Learn more about Simulink: https://goo.gl/nqnbLe
See what's new in MATLAB and Simulink: https://goo.gl/pgGtod

© 2021 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc.
See www.mathworks.com/trademarks for a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.