To find out how many items this design at right would have for 1,000 words, simply do 1,000x1,000=1,000,000. You can see there is 25 items for 5 words, and would have 36 items for 6 words, and 16 items for 4 words. If w2v had 1,000 words and 500 dimensions, it'd be 1,000 words x 500 axis items, 500,000 items. Half the size. 10,000x10,000=100,000,000, w2v would be 10,000x500=5,000,000, x20 more storage. It therefore seems efficient enough to actually implement, as 40,000 words is how many the human adults knows. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Ta664aad057469d5c-M6988bfc70f7369d0a7db7626 Delivery options: https://agi.topicbox.com/groups/agi/subscription
- [agi] Google - quantum computers are getting close immortal . discoveries
- [agi] Re: Google - quantum computers are getti... immortal . discoveries
- Re: [agi] Re: Google - quantum computers a... Rob Freeman
- Re: [agi] Re: Google - quantum compute... rouncer81
- Re: [agi] Re: Google - quantum com... immortal . discoveries
- Re: [agi] Re: Google - quantu... rouncer81
- Re: [agi] Re: Google - quantu... Rob Freeman
- Re: [agi] Re: Google - qu... immortal . discoveries
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google ... Rob Freeman
- Re: [agi] Re: Google ... rouncer81
- Re: [agi] Re: Google ... rouncer81
- Re: [agi] Re: Google ... immortal . discoveries
- Re: [agi] Re: Google - quantum com... immortal . discoveries
- Re: [agi] Re: Google - quantu... rouncer81
