One advantage vision modeling has is its close association with modeling physical objects. The most obvious example of this would be using 3D modeling and rendering engines to compress motion pictures.
On Sun, Nov 24, 2019 at 8:41 PM Matt Mahoney <[email protected]> wrote: > > > On Sun, Nov 24, 2019, 8:05 PM <[email protected]> wrote: > >> I thought you only need 1gb of training. ;) >> > > You need 20 years of text to train a language model. That's on the order > of 1 GB. > > You need 20 years of video to train a vision model. Each eye has 137M rods > and cones. Assume 10 bits per second each. That's 216 petabytes > uncompressed. > > I have enough computing power to study language. > >> *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/T3d8826b1a4fec947-Md8af1f979ef742962950de3e> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3d8826b1a4fec947-M6f97ba4a44c660ebefd2c269 Delivery options: https://agi.topicbox.com/groups/agi/subscription
