• Facebook
    • The ā€œlink things that are close in distanceā€ system we created yesterday: Link Creation Support.
    • It is the same as Curiosity Module written in Subjectivity and Emotion up to the point where the distance between past memories is calculated.
      • The ā€œCuriosity Moduleā€ is not a separate page at this time, but should become one eventually.
    • Now itā€™s a simple Euclidean distance, but when using cosine similarity, it takes the same form as inner product attention.
    • It seems relevant to this that I excluded the ones where the vectors are equal. - Independent Desire Device
    • Picking up the closest past memory from the new input and linking to it is ā€œassociativeā€ where the pickup is ā€œassociativeā€ and stocked with - Stock of associations
    • If we can describe what would be desirable, we may be able to acquire measures - Knowledge Weaving Program
    • What we havenā€™t done yet
      • I am able to find the closest memory Y for input X, but when I observe myself I am doing ā€œreading both and making new outputs with that stimulusā€, how can this process be achieved?
        • (11/4)
          • Associative indication is a primitive form of output
          • image
          • If the contents are combined in a different arrangement than originally given, the corresponding vectors will naturally be different.
            • The act of selecting and pointing to the closest content from this new vector is ā€œthe act of outputting a new combination of content as input.
    • There are 2^768 ways to do a Dropout in 768 dimensions, so a full search is practically impossible; if X and Y are associated under a certain Dropout and the connection is beneficial, it suggests that ā€œthat Dropout way is a beneficial abstractionā€.
      • So the connection of two points, ā€œthe connection of X and Yā€, is another data point one layer above, so that should be stocked too!

This page is auto-translated from /nishio/ę€č€ƒć®ēµēƀē‚¹2019-10-31 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. Iā€™m very happy to spread my thought to non-Japanese readers.