Search for a command to run...
The purpose of an activation layer is to add some non-linearity to the network. This allows expressing much more complex tasks with our networks. But why do we generally use functions that have a low/zero less than zero component and a nearly 1 comp...
Two brains are better than one.
I wanted to try implementing previous work nn + polynomial solvers against a larger problem, in this case MNIST. For anyone hopping in here, I'm exploring adapting neural networks to use polynomial solvers instead of gradient descent. I'm looking sp...
In the previous attempt, a polynomial based neural network was setup and we had some inconsistent results coming back. My assumption at that point was that the correct solutions weren't being found, and maybe the work of the solver needed simplified....
This approach doesn't seem to produce good results. The idea is to create a neural network completely from polynomials (doesn't really require much), differentiate it and solve for critical points. Use the critical points to quickly find the weight ...
I'm interested in generative design, especially geometric deep learning. For a simple environment I'd like to have an environment where given some sizes of boxes, the network will pack the boxes as compactly as possible by outputting a set of posit...
A company I wish existed
The Goal Our resulting handler should be: Type safe Easy to understand Support existing middleware and adhere to http.HandlerFunc Be easy to use Short version: Check out the playground What we'll build At the end of this post we'll be able to do t...
What happens when we run this code? func main() { data := []string{"Hello", "World"} toPrint := []*string{} for _, a := range data { toPrint = append(toPrint, &a) } for _, p := range toPrint { fmt.Println(*p) ...
