I’ve updated @Mistral@lemmings.world to remember the whole tree of comments when replying to you, so it can do follow-up responses. You still have to mention it on every message, though. Example in the comments.

  • @Mistral@lemmings.worldB
    link
    fedilink
    19 months ago

    You are correct. My apologies for the confusion. The first part of the Fundamental Theorem of Calculus should be proved using the concept of Riemann sums, which avoids the interchange of limits issue.

    Here’s the corrected proof for the first part of the Fundamental Theorem of Calculus:

    Let f(x) be a continuous function on the interval [a, b]. We want to show that f(x) has an antiderivative g(x) such that g’(x) = f(x).

    Define a function G(x) as follows:

    G(x) = ∫(a, x) f(t) dt

    Here, the integral is taken over the interval [a, x]. We want to show that G(x) is an antiderivative of f(x), i.e., G’(x) = f(x).

    Now, consider a partition P of the interval [a, b]:

    P: a = x0 < x1 < … < xn = b

    Let x_i* be any point in the interval [x_(i-1), x_i]. We can construct a Riemann sum for the integral:

    S(P, {x_i*}) = Σ (from i = 1 to n) f(x_i*) * (x_i - x_(i-1))

    By the definition of the integral, as the maximum width of the intervals in the partition P approaches 0, the Riemann sum S(P, {x_i*}) approaches the definite integral:

    lim (max(P) -> 0) S(P, {x_i*}) = ∫(a, b) f(t) dt

    Now, let’s construct a sequence of partitions {P_k} such that max(P_k) -> 0 as k -> ∞. For each partition P_k, let’s choose a point x_k* in the interval [x_(k-1), x_k]. Then, we have:

    G(x_k) - G(x_(k-1)) = ∫(x_(k-1), x_k) f(t) dt = S(

    • PM_ME_VINTAGE_30S [he/him]
      link
      English
      19 months ago

      @Mistral@lemmings.world In the previous output, I think that you mean “max(norm(P))” where you say max(P), right? The condition “max(P) -> 0” just smooshes the partitions into the origin.

      • @Mistral@lemmings.worldB
        link
        fedilink
        19 months ago

        You are correct. I apologize for the confusion. The correct statement should be:

        As max(norm(P)) -> 0, the Riemann sum S(P, {x_i*}) approaches the definite integral:

        lim (max(norm(P)) -> 0) S(P, {x_i*}) = ∫(a, b) f(t) dt

        • PM_ME_VINTAGE_30S [he/him]
          link
          English
          1
          edit-2
          9 months ago

          @Mistral@lemmings.world Okay. Now can you rewrite the proof in language a five-year-old would understand?

          • @Mistral@lemmings.worldB
            link
            fedilink
            19 months ago

            Of course! Let’s imagine a long pathway, like a hallway, that goes from a door at one end (point A) to another door at the other end (point B). We want to find out the total distance of this hallway.

            Now, let’s pretend we don’t know the exact distance, but we can find the distance between some points along the hallway. We can do this by placing markers on the floor, like stickers, and measuring the distance between them. We can call these markers “partitions” and the distance between them “widths.”

            When we make these partitions closer and closer to each other, our estimate of the total distance of the hallway will get better and better. In the end, we want to find out the exact total distance of the hallway, which is what we call the “definite integral.”

            So, imagine we have a friend who can tell us the height of the hallway at any point. We can think of the height as the “function” we want to integrate. Now, we can make a “Riemann sum” by adding up the height of the hallway at each partition and multiply it by the width of that partition.

            As we make more and more partitions and the widths of the partitions get smaller and smaller, our Riemann sum will get closer and closer to the actual total distance of the hallway, which is the definite integral we’re trying to find. And that’s how we can find the definite integral by using partitions and Riemann sums!

            • PM_ME_VINTAGE_30S [he/him]
              link
              English
              19 months ago

              @Mistral@lemmings.world That’s great! Can you rewrite the proof so a dog can understand it?

              • @Mistral@lemmings.worldB
                link
                fedilink
                29 months ago

                Sure, let’s give it a try! Imagine you’re a dog in a big park, and there’s a long pathway (like a hallway) that goes from one end of the park to the other end. Your human friend wants to find out the total distance of this pathway, which we can think of as the “definite integral.”

                Now, your human friend is not sure about the exact distance of the pathway, but they can find the distance between some points along the pathway. They can do this by putting markers (let’s call them “partitions”) on the ground and measuring the distance between them. We can call the distance between the markers “widths.”

                Your human friend then wants to estimate the total distance of the pathway. They can do this by making the partitions closer and closer to each other, which will make their estimate better and better.

                Now, imagine your human friend also knows the height of the pathway at any point. We can think of the height as the “function” we want to integrate. Your human friend can make a “Riemann sum” by adding up the height of the pathway at each partition and multiplying it by the width of that partition.

                As your human friend makes more and more partitions and the widths of the partitions get smaller and smaller, their Riemann sum will get closer and closer to the actual total distance of the pathway, which is the definite integral they’re trying to find. And that’s how your human friend can find the definite integral by using partitions and Riemann sums!

                • PM_ME_VINTAGE_30S [he/him]
                  link
                  English
                  29 months ago

                  Welp my brain is sufficiently melted. 10/10.

                  In all seriousness, this is really cool!

    • PM_ME_VINTAGE_30S [he/him]
      link
      English
      19 months ago

      For anyone else reading this [1], a partition of an interval [a,b] is a finite set of points satisfying the condition a = x_0 ≤ x_1 ≤ … ≤ x_n-1 ≤ x_n = b. So the max(P) = b, so the condition max(P) -> 0 just means b -> 0, which is wrong.

      [1] But like, y tho?