Full Stack Deep Learning
Search…
Full Stack Deep Learning
Course Content
Setting up Machine Learning Projects
Infrastructure and Tooling
Data Management
Machine Learning Teams
Training and Debugging
Overview
Start Simple
Debug
Evaluate
Improve
Tune
Conclusion
Testing and Deployment
Research Areas
Labs
Where to go next
Guest Lectures
Xavier Amatriain (Curai)
Chip Huyen (Snorkel)
Lukas Biewald (Weights & Biases)
Jeremy Howard (Fast.ai)
Richard Socher (Salesforce)
Raquel Urtasun (Uber ATG)
Yangqing Jia (Alibaba)
Andrej Karpathy (Tesla)
Jai Ranganathan (KeepTruckin)
Franziska Bell (Toyota Research)
Corporate Training and Certification
Corporate Training
Certification
Powered By
GitBook
Conclusion
What are the key takeaways to troubleshoot deep neural networks?
Conclusion - Troubleshooting
Summary
Deep learning debugging is hard due to many competing sources of error.
To train bug-free deep learning models, you need to treat building them as an iterative process.
Choose the simplest model and data possible.
Once the model runs, overfit a single batch and reproduce a known result.
Apply the bias-variance decomposition to decide what to do next.
Use coarse-to-fine random searches to tune the model’s hyper-parameters.
Make your model bigger if your model under-fits and add more data and/or regularization if your model over-fits.
Previous
Tune
Next - Course Content
Testing and Deployment
Last modified
2yr ago
Copy link
Contents
Summary