Matthew
• Member for 3 years, 5 months
• Last seen more than a week ago
• Boston, MA, United States

13k views

Generally speaking, best practice is to use only the training set to figure out how to scale / normalize, then blindly apply the same transform to the test set. For example, say you're going to ...

2k views

You're asking two questions here. Does this mean the magnitude of the vectors is irrelevant? Yes. Cosine distance is $D_{cos} = \frac{A \cdot B}{\|A\|\|B\|}$, which just comes from the definition ...

702 views

Your notation is a little confusing, but I suspect this is because you're not reading the original equation exactly right. $\mathbb{E}_{x \sim p_{data}(x)}$ means &quot;the expectation over $x$ drawn ...

172 views

You normalized it after splitting into train / test / validation, but you're doing this wrong. You need to normalize the training set X_train_normalized = scaler.fit_transform(X_train), and then use ...

66 views

I think it depends on what exactly you're doing with the GANs. If you're generating images, the two most popular (to my knowledge) are the Inception Score [1] and Frechet Inception Distance [2]. GANs ...

5k views

The value of the loss function depends upon the prediction (which is a function of the input data and the model parameters) and the ground truth. Gradient descent works like this: Initialize the ...

4k views

I'm not totally sure exactly what you're doing with your scoring equation, but the first thing you need to look at is your loss function. Categorical Crossentropy is for multilabel classification, and ...

54 views

You can absolutely get this information, but not from the confusion matrices. You want to be comparing the prediction vectors themselves, not the confusion matrices, because as you've rightly ...

1k views

Welcome! You haven't given us enough information to be able to diagnose this issue completely, but you should check your grid search code to see how each cross-validated model is being trained and ...

81 views

If I remember correctly, non-negative matrix factorization (NMF) can be used as a clustering approach that can recover clusters that are along vectors, for example. It may work for your dataset. It ...

96 views

In section 2.2.1 of the paper, they state that they use euclidean distance. I'm going to take your word that there are 512 filter activations in that layer; if I'm reading this right, there aren't ...

4k views

The original blog post mentions that the interpretation layer reduces the overall parameter size of the model, although I couldn't figure out by how much. It doesn't look like your network has that, ...

20 views

Round up or down to a whole number. Keras documentation specifies that units should be a positive integer, and I'm not sure what a fractional unit would even mean. Does this work when you try to run ...

3k views

I think your hunch is right. The generative loss can't improve because any movement the network would make towards reducing it comes with a huge penalty in the form of the latent loss. It looks like ...

64 views

I think you need to come up with a way to treat the data such that you're thinking in days, not hours, right? The peaks look they're just at 24, 48, 72, 96, (1 day, 2 days, 3 days, 4 days) etc, and ...

55 views

This is an active area of research called Human Activity Recognition. There are several public datasets available to cross-validate your methods, and you might want to start here: UCI HAR Dataset. ...

75 views

This is a big field in deep learning. You're going to want to search on network pruning, which is a method of model compression.

309 views

First of all, this is a binary classification problem (positive sentiment / negative sentiment), correct? And the dataset is roughly balanced? What were you trying to achieve by sorting them by length?...

71 views

Definitely (2). You should not include the testing values when calculating features over the data (or normalizing or scaling the data, etc). Let's take a step back for a second. Why are we holding ...

33 views

I think you should start by looking into Multi-label Classification, as your problem seems to be a subset of MLC, where one example can have multiple correct labels. If one class is "Pictures with ...

3k views

Do you need specific edges or just a set sparsity level that doesn't change? I know Keras allows you to pass a random seed to the dropout layers. If I understand what you need correctly, you could ...

2k views

I think that for the most part, the ends justify the means when it comes to learning rates. If the network is training well and you're confident that you're evaluating its generalization properly, use ...

728 views

There's actually some pretty interesting research on this topic. Key words would be model compression or CNN pruning (doing things like reducing the model size by removing filters with low activations)...

135 views

Try changing your kernel regularizer. Either reduce its effect or shut it off entirely, then retrain and see what happens. EDIT: I expect that the kernel regularizer is your best bet. You could also ...

4k views

I would really try not to use ordinal numbers for categorical data. It imposes a false magnitude and ordering in the model, especially when you have 1,000 examples. For example, the difference between ...

942 views

A few things: Are you sure your data / labels are set up correctly? Is every example of each class exactly the same? Most importantly, why are you using mean squared error? Shouldn't your target ...

519 views

A neural network is probably a perfectly reasonable approach here. But this is an extremely unbalanced dataset and you're going to have to handle that somehow. The network is learning that the best ...

54 views

Cross-entropy is an information-theoretic measure about probability distributions, and it's measured in units that are determined by the base of the logarithm used in its computation (nats for the ...

784 views