Tweeted By @OriolVinyalsML
Great post by Prof. David McAllester on why discrete representations matter, based on our findings in VQ-VAE2. "Vector quantization seems to be a minimal-bias way for symbols to enter into deep models."https://t.co/0vpG2Vtnt4https://t.co/lQgMjFl1tV pic.twitter.com/GbuLBAkcDN
— Oriol Vinyals (@OriolVinyalsML) June 28, 2019