75 points by lexandstuff 2 days ago | 5 comments | View on ycombinator
noduerme about 3 hours ago |
agnosticmantis about 3 hours ago |
It's not that the models magically "intuit" meaning from a blob of weights, but they methodically iterate on setting the weights with reasoning similar to a human engineer's reasoning.
robrenaud about 6 hours ago |
It's interesting to see how tolerant of tedium the models are.
I'm looking forward to the day we can have an optical device that runs only on light input, that looks like a piece of quartz, that you can place over a handwritten number (0-9) and on the top it displays the number in a clean font. Where the neural network to handle this can be translated into physical transformations once it's discovered, no inference processing power required.