Source: Unsplash

Training Neural Networks on Data That’s Lying

Learning from corrupted data

Oh no! You find out that your data is corrupted — there are enough instances of training data being attached to the incorrect label for it to be a significant problem. What should you do?

If you want to be a radical optimist, you could think of this data corruption as a form of regularization — depending on the…

--

--

--

ML enthusiast. Get my book: https://bit.ly/modern-dl-book. Join Medium through my referral link: https://andre-ye.medium.com/membership.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

What has Deepmind ever done for AI in games?

Neural Engineering, NER ’19 Notes

What dog breed am I?

Synthesize Hazy/Foggy Images using Monodepth and Atmospheric Scattering Models

Buying Propensity of Smartwatches

A fascinating approach to deep generative design

Lots of wheels with different designs. All generated using GANs and TopOp

Neural network pruning with simulated annealing

Work Flow in Machine Learning Project

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Andre Ye

Andre Ye

ML enthusiast. Get my book: https://bit.ly/modern-dl-book. Join Medium through my referral link: https://andre-ye.medium.com/membership.

More from Medium

4 Methods to Unbox the Machine Learning Models Black Box

Predict Prime Numbers — Error Convergence Using Data Science

Transformer’s Data Loader

The Ethical Data Scientist: Building Better Machine Learning Models