On Tuesday, November 09, 2021, at 11:17 AM, James Bowery wrote: > If you randomize the wrong literals, you may find >>>for some purposes<<< the > resulting output to be of less >>>value<<<. It all depends on the value > function of your decision tree.
Yes, for example the category of "visually lossless". It's basically lossy but visually the loss is undetectable. And regions of data can be replaced by small programs generating data were the diff is not perceptible. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5ff6237e11d945fb-M553fdd70de90e6a81c2b1cb2 Delivery options: https://agi.topicbox.com/groups/agi/subscription
