-
Using the raw spectrograms as input features, the best AUC I got is 0.9307. The configuration was the following:
```
DBN(dropouts=0, epochs=30, epochs_pretrain=0, fan_outs=None, l2_costs=0.0001,
l2…
-
I applied your dbn.cpp code . But for your all test data, the prediction results are equal. It is an unexpected situation (if we give a training sample as a train sample it can not find the true class…
-
Hello, I feel deeply after reading your paper 'An Intrusion Detection System based on Deep Belief Networks'. I have to say, your ideas and abilities are great.But I have a question. Your paper mention…
-
[Unsupervised feature learning for audio classification
using convolutional deep belief networks](http://www.robotics.stanford.edu/~ang/papers/nips09-AudioConvolutionalDBN.pdf)
-
Background
Protein quality assessment (QA) useful for ranking and selecting protein models has long been viewed as one of the major challenges for protein tertiary structure prediction. Especially, e…
-
They should run in less than a second, as unit tests. Even with debug mode enabled! (Thats mostly when one runs them). Good to get in shape before release
I reference people who might be able to fix t…
-
When deep belief network is implemented for representation learning, I'm confused about the representation of hidden layers for the original data matrix.
The method sigmoid_layers[-1].output seems doe…
-
[Visualizing Higher-Layer Features of a Deep Network](http://www.iro.umontreal.ca/~lisa/publications2/index.php/publications/show/247)
Deep architectures have demonstrated state-of-the-art results in…
-
Would the following be best managed as external dependencies rather than included in this repository? It would keep the repository much smaller and may make it easier to switch to newer versions of d…
-
### Deep Learning for Imbalance Classificaition
#### Survey
1. [A systematic study of the class imbalance problem in convolutional neural networks
Cost-Sensitive](https://arxiv.org/pdf/1710.05381.p…