-
Here is the buggy code from filler.hpp line 77. As mentioned in the comment, the number of inputs is taken from blob->height() when it actually should be blob->width(). I first noticed this error wh…
-
The final goal of cuSAE is to train a sparse autoencoder to classify the MNIST dataset, while using CUDA C to implement expensive computations.
First we need to add MATLAB code that imports the data…
-
I save out a network like so:
e = Experiment(Regressor, layers=(input_layer, hidden1, output_layer), optimize='hf', num_updates=30, verbose='True')
e.run(dataset, dataset)
e.save('network.dat')
The…
-
PCA, SVD(其他low rank*), LDA(Topic Model), K-means, Sparse Coding,Hidden Layer of Neural Network。。。等等这一大类问题应该都可以用一套理论来解释其几何意义,与向量空间、矩阵、特征值和特征向量有关的,有阐述最本质原理的文章? 比特征值和特征向量更低层的?@好东西传送门
http://www.weibo.com…
-
Hello, I am trying to install the multisearch pacakge from package manager but seems I can not find the package. Is it available now and what the name is it? Following is the package list I found -
…
-
Lasagne `Layers` compute their outputs by calling `get_output()` recursively on their parents. When a network has a tree structure, which is usually the case, this works fine. But when a network has a…
-
This [gist](https://gist.github.com/kastnerkyle/6315027) sums up what I am seeing. When I try to do an overcomplete autoencoder, the sparsity for all decode layers shows up as 1. and the cost gets "st…
-
Is there currently any way to add a sparsity constraint to the cost of an autoencoder? I see regularization terms (weight_l1, l2, etc.) but another [tutorial](http://easymachinelearning.blogspot.com/p…
-
pylearn2/models/sparse_autoencoder.py:
ImportError: cannot import name DenoisingAutoencoder (line 6)
and
pylearn2/utils/datasets.py (line 17)
from pylearn2.datasets.utlc import get_constant, sharedX
-
Is there an easy way to implement L1 regularization on the weight matrix of a fully connected network. Similarly I want to penalize the L1 norm of features in each layer. What is the best way to do th…