New answers tagged

1

It depends on the task the agent is trying to learn and of course on the environment constrains. In an Atari game agents have a pre-fixed starting point because that's part of the games rules, so I would say that this is enough of a justification to make each simulation start from that starting point. Moreover, you have to pay attention to the kind of ...


1

Batch size and epochs are independent parameters - they serve very different purposes. Your main question as I understand it (and for general, non-library specific consumption) is what is an epoch and how is the data used for each epoch? Simply put, an epoch is a single iteration though the training data. Each and every sample from your training dataset ...


0

ok so let me explain in my word how i understood this process: i know that one sample mean one row, therefore if we have data with size(177,3), that means we have 177 sample. because we have divided X and y into training and test, therefore we have following pairs (X_train,y_train) and (X_test, y_test) now about batch size, if we have let say 177 ...


1

Recognising intents is only a small step in developing a chatbot. It's fine to use an ML classifier with training data for that, no need to keep the original list of intents. However, you should really think about the next step: how are you getting your bot to conduct a dialogue, rather than firing off single responses to user queries. That is where things ...


1

There are other sources that will lead to different results in addition to weight initialization. For example dropout layers. Make sure you specify the random seed.Also data reading using flow from directory,make sure you set shuffle to False or if you do not then set the random seed. If you use transfer learning make that part of your network non-trainable. ...


0

End to end means deep learning is the only thing that is used. Many people have doubts on its viability though, I certainly do. I wouldn't trust an end-to-end DL based self driving car.


0

You should at least crop the plots and add a legend. Maybe also provide some scores (accuracy, auc, whatever you're using). Anyway, it doesn't look your model is underfitting, if it was you should have high error at both, training and test phase and the lines would not cross.


1

Running for "to many" epochs can indeed lead to over fitting. You should look at the validation loss. If on AVERAGE it continues to decrease then you are not yet over fitting. You may be tempted to run more epochs in hopes your loss will decrease but unless you adjust your learning rate dynamically at some point you won't get any improvement. If you use ...


1

Training a neural network for "too many" epochs than needed without using early stopping criterion leads to overfitting, where your model's ability to generalize decreases.


Top 50 recent answers are included