Deep Neural Networks
topic on 4 shows · 4 statements across 4 episodes
the Y Combinator Startup Podcast 
the MAD Podcast 
How I Built This 
the a16z Podcast
4 statements about Deep Neural Networks, every show
Altman: Deep neural networks showed performance scaling with compute in 2012
“And then in 2012 deep neural networks started to work. And not only did they start to work, it appeared that the more compute you threw at them, the better they got.”
Deep neural networks are easily fooled by abstract adversarial visual patterns
“In fact even our sophisticated deep neural networks can be fooled very easily by showing creating these weird-looking patterns, and those patterns will get interpreted with very high confidence as, you know, things like starfish, freight car, remote control et…”
Schönlieb: Deep neural networks outperform handcrafted methods in image denoising
“Image denoising nowadays, I think the best image denoising approaches are actually coming from deep neural networks. So, you know, these handcrafted methods get more and more beaten in terms of performance. By some of these neural network approaches.”