Categories for AI 3: Categorical Dataflow: Optics and Lenses as data structures for backpropagation

[@johnhart1790]

@ 26:42 that should be F(g): F(B) -> F(C) for covariant functor F

[@muttdev]

In the notation X ⊗ Y, Are X, Y objects or morphisms? So far small letters f,g,h were used to represent morphisms and capital letter A,B,X,Y were used to represent objects in a category. That is why I am having confusion about X and Y

[@Jacob011]

About the diagrams @ 37:30: This is pedagogical suicide! How can you just drop on us diagrams in a graphical language we've never seen before and expect us to reason about them? We don't even know what the boxes represent, what the lines connecting the boxes represent, etc. We don't know how to read these diagrams!! It was immediately clear to me what the students were asking about: apparently reshuffling parts of the diagram produces a different diagram (hence why they were asking about the "box position encoding information") For someone who understands category theory, it sure as hell shouldn't be a problem to understand that people can't know what you haven't told them yet!!!

[@anduong334]

I totally agree with you! I felt like becoming a dumbass because of that diagram which suddenly coming from the middle of nowhere. I was still on track with the previous slide about the Tensor operator. But then the diagram was introduced as a question, which entirely made the previous slide irrelevant. Even more, I had no clue about the context of the diagram or any basic information to interpret it. What were the boxes? What did the f, g, h, i mean? What did the lines connecting the boxes mean? Though I already had fundamental knowledge in Category Theory. (For anyone who want to grab fundamental knowledge of Category Theory and its core philosophy, I highly recommend the book The Joy of Abstraction by Eugenia Cheng) Later, thanks to the question of an audience, which is necessary to clear things out, I could catch up a bit after the explanation of the speaker. I think this lecture should be considered a better way to present it to its audience who might come from different backgrounds

[@franzschlicht1307]

How did Grav. do the animated gifs in his presentation? Did he draw them frame by frame?

[@muttdev]

In monoidal category, what are the objects, morphisms and composition?

[@mateuszbaginski5075]

~anything; these are not included in the definition of a monoidal category e.g., there are monoidal categories where objects are sets, functors, lenses, etc

[@dirrelito]

Nice understandable lens explanation. Thanks!

[@ryderbrooks1783]

The ipad drawing thing is a crutch for the presenter. It introduces unnecessary points of confusion for the viewer while giving a false sense of clear communication to the presenter. Watching you scribble the chain rule for a trivial example is a waste of my time even at 2x.