New answers tagged

0

There are a lot of questions to be asked about your test setup, data preprocessing, and model architecture. RNNs, or in your case LSTMs, can be tricky when it comes to implementation. I suspect your problem lies somewhere with the LSTM or preprocessing. Are all lat/lon data points in one class the same? If not one thing you might want to do is to somehow ...


0

I think you can solve this problem with models trained for Named Entity Recognition. In that case, your entities are labels. To do this you can use spacy to train a NER model or more easily you can fine-tune a Distil-BERT for your task.


2

As you can see in Fig. 2 of the WaveNet paper the receptive field is 5, but the input size is larger (16). The receptive field defines what a single output neuron can see (see arrows in Fig. 2). The receptive field could also be greater than the input, e.g. if you want to use or you only have the last 12 time steps and use the following structure (WaveNet ...


1

That drawing it's a bit oversimplified. Check this blog for a better explanation and implementation details. I'll refer to the image they have to answer: the yellow boxes represent embedding layers, required to convert words in numbers the green boxes represent the unfolded encoder the red box represent the context vector, i.e. the vector you're looking for....


Top 50 recent answers are included