Richard Baraniuk

Professor at Rice University (machine learning, signal processing) and Founder/Director of OpenStax (open education)

[Imtiaz Humayun @imtiazprio]

Does recursive training of generative models only lead to a loss of diversity or is there more?

We show that 'self-consuming' generative models don't only face model collapse, they can emphasize hidden artifacts of the generative model as well!

https://t.co/bQFBmQlWfv

🧵(1/N)

[Rice DSP Group @rice_dsp]

It is not what a deep net can approximate that matters, but how it learns to approximate. Matrix perturbation theory explains why the loss surface of a ResNet or DenseNet is less erratic and eccentric than a ConvNet and hence easier to optimize under SGD https://t.co/BypTblnPZt

[Richard Baraniuk @rbaraniuk]

Engineering is art informed by science.