New answers tagged

2

As a disclaimer, I didn't read that page, but I can certainly explain where the derivatives come from. The backpropagation algorithm is actually a variant of the gradient descent algorithm. Think about a single function for the moment. Suppose you have a function which responds to a single input and a single weight: $f(w, x)$. We want to adjust $w$ so that ...


1

I have wondered something similar and failed to find much in the way of satisfying answers in the literature. Here is what I tentatively came up with. It seems perhaps what we need is some kind of regularization. If $\theta$ is a model (say, a regular expression), let $c(\theta)$ denote some measure of the complexity of the model (say, the size of the ...


0

I don't think that paper is suitable for what you want to do. That paper generates an embedding of nodes: given a graph $G$ and a node $v$ in $G$, it outputs an embedding of $v$ (a representation of some properties of $v$). You want an embedding of the entire graph: given a graph $G$, you want to compute an embedding of $G$ (a representation of the entire ...


0

This is called top-3 accuracy. See https://stats.stackexchange.com/q/95391/2921, https://stackoverflow.com/q/37668902/781723, https://stats.stackexchange.com/q/156471/2921. Sure, you can use it. Whether top-1 accuracy or top-3 accuracy is better correlated with user satisfaction will depend on your particular application and on your users.


2

Computer science is a very broad subject area, and many of its sub-disciplines have little or no overlap with others. For example, knowing the basics of operating systems design, compiler design or microprocessor design are unlikely to help you make progress in machine learning (although each one is an interesting topic in its own right). Machine learning ...


0

You can check Natarajan, On learning sets and functions or Haussler and Long, A generalization of Sauer's lemma.


Top 50 recent answers are included