deep-river
deep-river copied to clipboard
online-ml
Is it possible for deep-river to take multiple inputs to a learned model and output multiple predicted outputs? For example tensorflow1 of the form model_output = self.sess.run([self.curr_nn_output], feed_dict={self.x_: inputs_list})，where inputs_list...
Hello, how does deep-river address conceptual drift and catastrophic forgetting?
If I have a model like this: ```python class Model(torch.nn.Module): ... self.user_embed = torch.nn.Embedding(n_users, n_factors) ... ``` What would be the best way to implement `def learn_one...` given that new...
Is it possible to use fine-tuned model with PyTorch and deep_river?
Request: Allow multi-feature output. e.g. allow the final layer to output a list or dictionary with one feature per element. [Here is a (probably incorrect) example of a way to...
The `learn_many`methods are actually not tested → Needs to be fixed
As we support Python 3.8. and dicts guarantee to [persevere order](https://stackoverflow.com/questions/1653970/does-python-have-an-ordered-set), we could get rid of `OrderedSet`
For LSTM-based models it would probably make sense to use the loss of the predictions over the entire rolling window (see figure below) since they are computed anyways to obtain...
