Have a question... These days more and more people are interested in deep learning, where distributive representations may be relevant.
In a distributive representation many units are shared to represent individual concepts. In my mind I visualize the concepts as a partition of the vector space: There is also the "principle of superposition" that says that 2 concepts can share the same vector space representation via vector addition. But here comes a problem: if we have 3 propositions, say P1 = yesterday rained P2 = Obama is president of US P3 = the moon is made of cheese and if there exists a linear dependence among them, say: a3 P3 = a1 P1 + a2 P2 where a1, a2, a3 are scalars, that seems to create a relation between apparently unrelated sentences, and would lead to error. So it seems that the principle of superposition cannot hold with distributive representations unless the dimension of the vector space is bigger than the number of concepts / propositions / objects that need to be represented. Maybe my understanding above is incorrect? What's the problem here...? -- *YKY* *"The ultimate goal of mathematics is to eliminate any need for intelligent thought"* -- Alfred North Whitehead ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
