On Sat, Mar 21, 2020 at 2:16 PM Matt Mahoney <[email protected]> wrote:
> A lossless compression contest on video would result in contestants > spending 99.9999% of their efforts on compressing data that the eye and > brain throw away, assuming the payoff is the same for both types. > "payoff" is relative to the utility function (SDT). There certainly is room for a contest that specifies the utility function but that niche is absolutely saturated with all of the labeled data contests including not just Kaggle but the entire machine learning industry since its all about engineering. Science, as usual, is left sucking hind tit. PS: Last time I looked there still wasn't a video codec that used 3D rendering hardware to decompress streaming video. That's a huge unexploited space in data compression that can yield equally huge returns -- and not just in saving network bandwidth during pandemic binge Netflix watching. Getting "the physics engine" right is what much of our nervous system is about, prior to more abstract inferences, and getting the 3D model right is prior to the physics. > Noise is not just white noise, but all the details in the scene that don't > increase your reproductive fitness. > > Also, you would need about 10-20 years worth to model human level vision, > or 100 exabytes at the eye's resolution. > > Text compression works because you only need 1 GB, and it's mostly signal. > > On Sat, Mar 21, 2020, 1:24 PM James Bowery <[email protected]> wrote: > >> >> >> On Sat, Mar 21, 2020 at 12:00 PM Matt Mahoney <[email protected]> >> wrote: >> >>> Data compression won't solve AGI. It's just a useful tool for evaluating >>> language models... >>> >> >> I'd put it more like "Data compression _alone_ won't solve AGI. It's >> just the gold standard for model selection. Model selection _alone_ won't >> solve AGI." >> >> >>> Compression is not so useful for evaluating images, video, or audio >>> models. >>> >> >> That doesn't mean it's not the gold standard for model selection. >> "usefulness" aka "utility"gets one into the Sequential Decision Theory >> aspect of AIXI. >> >> >>> Lossless algorithms are overwhelmed by incompressible noise. >>> >> >> As long as two models are challenged with _exactly_ the same data, the >> small differences make all the difference in terms of model selection. One >> man's noise is another man's ciphertext. >> >> > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/T2a0cd9d392f9ff94-M9537928c153ea765257d3706> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T2a0cd9d392f9ff94-M2c466e147b3d3b3285a2499f Delivery options: https://agi.topicbox.com/groups/agi/subscription
