btw, many will not find this even offered at their high school. Here, math skills become extremely important. It's because evaluation requires more than boiling down performance to a single number. I'm sure that anyone that hacks around with LLMs or diffusion will understand how leaderboards are often noisy and how picking top models does not guarantee top performance (and why datasets get continually added). Complexity in evaluation only increases as our performance increases and a major problem we face today is we are marginalizing out important information. But I think we need to be clear about these distinctions as model evaluation gets insanely complex. You don't need this understanding to build models (as you also conclude) and most researchers don't understand much of this either tbh. Even understanding something like activation functions take much higher level math as we got to get into topics such as topology, metric theory, and high dimensional statistics. BUT that doesn't mean there isn't a lot of math hiding around in the background. Yes, many parts of ML only require multivariate calculus and those are the parts that most people are exposed to. > Indeed, deep learning math is basically senior-high-school level calculus.Īctually I find this claim problematic and incorrect. But using those libraries doesn't make you an expert in computer graphics. I'm not a graphics expert, but I use graphics programs every day, and graphics libraries regularly. I use many libraries doing things I don't fully understand. That's not a ding against those whose main experience with DL is using those libraries. That's like saying knowing how to use GCC gives you a solid understanding of compilers. That being said, I don't think understanding how the `transformers` library works or composes is the same as understanding how 'deep learning' works. The only change was the advent of large enough data and computer chips to process it. The math for deep learning has been set in place for more than fifty years at this point. There is really no surprising thing or deep insight. Backpropagation is a straightforwards application of the chain rule. Indeed, deep learning math is basically senior-high-school level calculus. One of the problems I see here is that it seems to me that the math education of many CS grads is woefully lacking. The post is not talking about 'traditional ML' but rather only 'DL' (i.e. In that sense, regardless of the etymology, the name actually fits. But nevertheless, the 'normal' meaning of kernel works out because kernels are typically the core fundamental operations supported by a machine learning framework atop which the other operations are built. I believe they come from operator theory and support vector machines. Nevertheless, it is the kernel of many common English idioms such as a 'kernel of truth'. So actually, the definition is the same, it's just that the word kernel is rather rare, despite having a well understood meaning. In linear algebra, the kernel of a matrix (or a linear transformation, same thing) is the set of vectors it maps to zero, which is also in a sense the 'core' of the mapping (in so far that zero can be seen to be at the 'core' of the vector space / number line). An OS kernel is the core of an operating system. In English, the word 'kernel' means 'core'. EDIT: Hacker news won't let me respond, but the answers below all seem to be because the original meaning has been lost on everyone.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |