New answers tagged

1

Try removing the dropout before the prediction layer. I couldn't find the paper or article I read about this (will update the post once I find it), just found a Cross Validated post which does not add much information. As you are If you are lowering the learning rate, you should also lower the batch size accordingly. As for Batch Normalization layers, they ...


1

What is the No Information Rate (NIR)? I.e. what are the percentages of positive and negative labels? Have you looked at the predictions of your model? If it's all 0's or all 1's then it probably learned nothing, other than predicting the majority class. When it comes to architectural choices and hyperparameters, especially if you start working with NNs, ...


0

It's an important feature, and you drop it at the risk of the agent failing to learn successfully. The difference between the TD target without the terminal flag $$G_t = R_{t+1} + \gamma \text{max}_{a'} Q(S_{t+1}, a')$$ and with the terminal flag applied to $S_{t+1} = S_T$ $$G_t = R_{t+1}$$ is important whenever $Q(S_{T}, a')$ might be evaluated as non-zero. ...


0

Generally when you see metrics stagnate like this it's because the model has converged incorrectly (ex: always predicting 0, or gradients/weights have dropped to 0, etc.). Can you see if this is what's happening for your problem? I'd expect that perhaps your model has converged to predict the majority class for each label.


Top 50 recent answers are included