← Back to context Comment by candiddevmike 2 months ago Running things through lossy compression is transformative? 1 comment candiddevmike Reply muldvarp 2 months ago The quotation marks indicate that _I_ don't think it is. Especially given that modern deep learning is over-paramaterized to the point that it interpolates training examples.
muldvarp 2 months ago The quotation marks indicate that _I_ don't think it is. Especially given that modern deep learning is over-paramaterized to the point that it interpolates training examples.
The quotation marks indicate that _I_ don't think it is. Especially given that modern deep learning is over-paramaterized to the point that it interpolates training examples.