3
Sure! There's all sorts of ways you can pass in two inputs. Your idea of stacking the inputs like a 2-channel image is one idea.
Another possibly simpler idea would be something like this:
The intuition is that the network learns intermediate representations for the two sentences, then compares the representations.
Of course, you have an enormous amount ...
2
There is plenty of methods to calculate feature importance. I recommend trying two of them LIME and SHAP.
I don't want to copy-paste material and tutorial provided by the author so please refer to these two repositories.
2
Machine translation using traditional neural architecture (seq2seq models) had various issues due to rare-words, low accuracy and slow translation [1]. Even after using various mechanisms like attention and residual connections the performance was only comparable (not better than) statistical phrase-based machine translations [1].
I can only think of this ...
2
It depends…
The general rule of thumb is that there should be at least 40 occurrences of an item to train an embedding model to find a robust representation. If most follower IDs repeat then an embedding model can learn which ones co-occur. If follower IDs are sparse then hashing (which randomly assigns numbers) is a better choice.
Which method is better ...
2
It could be your model or your data. You need to perform the experiment of changing your model (while holding data constant) to isolate the causal reason.
Yes - models can get worse with more data. One of the primary reasons is models often have a limited capacity to learn. Simple models can only successfully model simple relationships. Again - if you fit a ...
1
Input data of LSTM() layers must follow this pattern:
( Number of observations , Window size , Number of input series )
Number of observations is the size of your mini batch; Window size is the length of each input series, another hyperparameter you can choose; Number of input series is the number of explanatory variables you are using.
1
Take the example of time series: $\mathbf{x}1,\mathbf{x}2,\ldots,\mathbf{x}10$ where each $\mathbf{x}i$ is let 5 dimensional. The 'timestep' here will be the window chosen such that value at time instant is dependent on previous $p$ lags. So data passed to LSTM will be of the form $\mathbf{x}1,\mathbf{x}2$ as input with $p=2$ lags. In your case as well, each ...
1
The way LSTMs are capable of learning long term dependencies is by keeping a cell state which serves as a memory of sorts.
This cell state is updated based on the values of different gates within the cell, forget gate being one of them.
The forget gate looks at the previous hidden state and the current input and outputs a number between 0 and 1 for each ...
1
An increase in validation loss while training loss is decreasing is an indicator that your model overfits. Check out this article for an easy to read general explanation.
In the context of autoencoders this means your neural net almost reproduces the input image. Try to reduce overfit by applying regularization, e.g. add dropout, add input noise, use less ...
1
I'll expand my answer if there is any interest. I propose building a simple test model using Vgg and two custom fully connected layers that end with a single sigmoid per the document below. If you prefer early fusion I recommend using stacked black and white images.
https://www.cs.cmu.edu/~rahuls/pub/cvpr2014-deepvideo-rahuls.pdf
if you then want to go the ...
1
First, you have too little data. 50 samples. Think of it. Of all possible 2001 sequences of that kind, you are only feeding 50 (less than 2.5%). Your question is actually a very good case to show the importance of big data for training a neural network.
And second, it is the problem stated in this arxiv article made by Uber empolyees - even a deep neural ...
1
Here are two ways to model the problem. The first one is simpler, the second one is more complex but closer to your original statement of the problem.
Store as an input feature
You can consider the store as a feature to pass to your LSTM. With two different stores, just add a binary input feature "store" where store A is 0 and store B is 1, for example.
...
1
If you are looking to predict multiple time series (which would be similar in nature, since each weather station in the area would record similar temperatures, even if they are not identical), using a separate LSTM model for each may prove quite time-consuming.
One approach you could take is one suggested in an excellent answer for another question on Cross ...
Only top voted, non community-wiki answers of a minimum length are eligible
