tag:blogger.com,1999:blog-247496708878499996.post197331680440759172..comments2022-03-01T21:28:56.852-07:00Comments on Undefined Intelligence: A First Experiment with Pylearn2daemonmakerhttp://www.blogger.com/profile/02667004579800812794noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-247496708878499996.post-56418658076963545382014-10-19T08:38:06.857-06:002014-10-19T08:38:06.857-06:00Yes, your right. The most basic ingredients are th...Yes, your right. The most basic ingredients are the dataset, algorithm, and model. I sort of say as much in the third paragraph of the YAML syntax section but I realize now it's stated outright so I will update.<br /><br />Regarding how the algorithm knows what parameters to optimize, the short answer is that the model exposes a list of the appropriate parameters via a member variable called _params. The inner workings of this part is really interesting but requires going into details about how Pylearn2 uses Theano, at least for the most part, so I will avoid it for now.<br /><br />As for whether models can be stacked, of course! Well sort of. :) I don't yet now to explicitly send the output from one model to the input of another. For instance I don't know how to send the output of an MLP to an Autoencoder. However in pylearn2.models.mlp there is a class called MLP that takes a list of layers and a specification of how to wire them together. That same module contains a number of different types of layers allowing for the construction of fairly complicated models. I still need to learn a bit about the inner workings with respect to convolutions but I believe these are actually treated as something called spaces which are descriptions of how the data should be transformed from layer to layer.daemonmakerhttps://www.blogger.com/profile/02667004579800812794noreply@blogger.comtag:blogger.com,1999:blog-247496708878499996.post-28917838989745283012014-10-18T19:35:32.345-06:002014-10-18T19:35:32.345-06:00I thought of a question. It seems like the most ba...I thought of a question. It seems like the most basic ingredients are the _dataset_, the _algorithm_, and the _model_, is that correct? How does the algorithm know what to optimize within the model?<br /><br />Also, is it possible to stack models, for example put a convolutional layer and a perceptron layer in the same model?Anonymoushttps://www.blogger.com/profile/15624261037800893086noreply@blogger.com