Is this OK for a chat bot?

Is this OK for a chat bot?

CRIME Shirt $21.68

Nothing Ever Happens Shirt $21.68

CRIME Shirt $21.68

  1. 1 month ago
    Anonymous

    I thought it would be a bunch of if/else

    • 1 month ago
      Anonymous

      You got lied to. It's actually a bunch of JNE

      • 1 month ago
        Anonymous

        >JNE
        What is that?

        • 1 month ago
          Anonymous

          asm for goto

          • 1 month ago
            Anonymous

            Oh, jump if not equal!

            • 1 month ago
              Anonymous

              yeah
              and a bunch of other's similar
              BNE, JNZ, etc.

              • 1 month ago
                Anonymous

                I'm just trying to make it so that my neural net outputs something readable.

              • 1 month ago
                Anonymous

                benzos? jengo!? what the FRICK are you on about?

              • 1 month ago
                Anonymous

                benzos? jengo!? what the FRICK are you on about?

                you guys have been playing jenga without me?

  2. 1 month ago
    Anonymous

    LGTM

  3. 1 month ago
    Anonymous

    I don't think a convolutional layer makes sense for NLP applications. Order of words matters a lot.

    • 1 month ago
      Anonymous

      Please explain.

      • 1 month ago
        Anonymous

        Convolution layers are useful when your data has positional invariance, such as visual data (image and video). Text, on the other hand, is almost never positionally invariant. See pic

        • 1 month ago
          Anonymous

          But it's not random

          • 1 month ago
            Anonymous

            what is this in response to

            • 1 month ago
              Anonymous

              The convolutional layer doesn't randomize the order does it?

              • 1 month ago
                Anonymous

                That's right it doesn't. The convolutional layer loses a lot of positional information (, that's not the same as randomizing order,) which is why it is bad for NLP where meaning is extremely sensitive to positional information.

              • 1 month ago
                Anonymous

                I just wanted my ot to "understand". Should I use LSTM?

              • 1 month ago
                Anonymous

                Yeah that's a good alternative.

              • 1 month ago
                Anonymous

                Doesn't it need to be iterative to work with an LSTM?

              • 1 month ago
                Anonymous

                Instead of asking one small question at a time, how about you take some time to figure out what you want and then come back after you've thought about it for a while.

              • 1 month ago
                Anonymous

                I've studied this for a short while, from what I understand LSTM has to be iterative. Conv would I presume find permutations that would still be valid and accept differently phrased text as the same.

    • 1 month ago
      Anonymous

      you CAN do CNN for NLP (see https://arxiv.org/pdf/1610.10099.pdf) and it was pretty popular 2013-2017 but transformers just werk
      language fundamentally has a tree structure so you need kernels at all distances if you want to do CNN

  4. 1 month ago
    Anonymous

    I love how designing neural networks is a combination of empirical research, esoteric ancestral knowledge and dudebro "common sense".

    • 1 month ago
      Anonymous

      I grok some of it.

  5. 1 month ago
    Anonymous

    >tf.keras.layers.Dropout

  6. 1 month ago
    Anonymous
  7. 1 month ago
    Anonymous

    The Conv2D neural net had figured out that there are words and was trying to decide what to use for the space.

Your email address will not be published. Required fields are marked *