TL;DR Your input data is not normalized. use x_data = (x_data – x_data.mean()) / x_data.std() increase the learning rate optimizer = torch.optim.Adam(model.parameters(), lr=0.01) You’ll get convergence in only 1000 iterations. More details The key difference between the two examples you have is that the data x in the first example is centered around (0, 0) … Read more
Your approach works fine, if the x and y component of the ray axis points in the positive direction, but it fails if it points in the negative direction. As you pointed out, that is caused by the way pygame.mask.Mask.overlap works: Starting at the top left corner it checks bits 0 to W – 1 … Read more
Three excellent and mature NLP packages are Stanford Core NLP, Open NLP and LingPipe. There are Ruby bindings to the Stanford Core NLP tools (GPL license) as well as the OpenNLP tools (Apache License). On the more experimental side of things, I maintain a Text Retrieval, Extraction and Annotation Toolkit (Treat), released under the GPL, … Read more
Judging from the existing answers, there seems to be a lot of confusion about this concept. The Problem Is Always a Graph The distinction between tree search and graph search is not rooted in the fact whether the problem graph is a tree or a general graph. It is always assumed you’re dealing with a … Read more
I think there is a lot of confusion about which weights are used for what. I am not sure I know precisely what bothers you so I am going to cover different topics, bear with me ;). Class weights The weights from the class_weight parameter are used to train the classifier. They are not used … Read more
Since you ask this very basic question, it looks like it’s worth specifying what Machine Learning itself is. Machine Learning is a class of algorithms which is data-driven, i.e. unlike “normal” algorithms it is the data that “tells” what the “good answer” is. Example: a hypothetical non-machine learning algorithm for face detection in images would … Read more
Here is a one hidden layer network with backpropagation which can be customized to run experiments with relu, sigmoid and other activations. After several experiments it was concluded that with relu the network performed better and reached convergence sooner, while with sigmoid the loss value fluctuated. This happens because, “the gradient of sigmoids becomes increasingly … Read more
For a virtual earth application I’ve used the clustering described here. It’s lightning fast and easily extensible.
You can think of it as the Binary Search Algorithm. In each iteration, we ask a question, which should eliminate roughly half of the possible word choices. If there are total of N words, then we can expect to get an answer after log2(N) questions. With 20 question, we should optimally be able to find … Read more