Lossy compression is confirmation bias. One man's noise is another man's cyphertext.
I finally got this through to the guy who Hinton, Werbos, McClelland and Rumelhart credit with financing the revival of connectionism in the 1980s. He's totally on board with lossless compression as the model selection criterion now. How long before Google gets their head out wherever it is stuck? ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8c8ee84b385720a5-M1d7d31aa333e2bb77da348f6 Delivery options: https://agi.topicbox.com/groups/agi/subscription
