• 1 Post
  • 399 Comments
Joined 3 months ago
cake
Cake day: March 28th, 2024

help-circle














  • Its already in your word. Proportional. A proportional control, or P control (generally, a PID with the K_I and K_D set to 0)

    Alright some edit as I will try to explain my answer. Say for example a value ‘x’ is > 0 and < 100 (so, 0 < x < 100). In this case, the point that you wanted to reach is 100, such that x is always getting bigger and closer to 100 (x->100). If you subtract x from 100, you get the remaining, call it ‘y’, that you need to add to get to 100 (y=100-x). So now, the rate of change must be proportional to that number. I.e., as x gets closer to 100, y will get smaller. How much faster is determined by a proportionality constant, that can be called K_P.



  • Well, this is just my 2-cent. I think you misunderstand the point I am making. First of all, accept that translation is a lossy process. A translation will always lose meaning one way or another, and without making a full essay about an art piece, you will never get the full picture of the art when translated. Think of it this way, does Haiku in Japanese make sense in English? Maybe. But most likely not. So anyone that wanted to experience the full art must either read an essay about said art or learn the original language. But for story, a translation can at least give you the gist of the event that is happening. Story will inherently have event that have to be conveyed. So a loss of information from subtlety can be tolerated since the highlight is another piece (the string of event).

    Secondly, how the model works. GPT is a very bad representation for translation model. Generative Pretrained Transformer, well generate something. I’d argue translation is not a generative task, rather distance calculation task. I think you should read more upon how the current machine learning model works. I suggest 3Blue1Brown channel on youtube as he have a good video on the topic and very recently Welch Labs also made a video comparing it to AlexNet, (arguably) the first breakthrough on computer vision task.