My pic above leaves out the learning part though. Glove takes very long to
train, it can go on for months. And needs way more than 40,000 words, more than
human brain knows! Seems wasteful. Anyway the new idea above on right side of
the pic would use a similar learning method, and it wouldn't chop the data into
a 500 dimensional space though. As for Online Learning, you tally up the
appearances, basically, which gives each link a score, and so you can always
later up it (update it), since you don't compute dimensional plotting.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Ta664aad057469d5c-M4ee18d81693c094715d83564
Delivery options: https://agi.topicbox.com/groups/agi/subscription
