Using the LSTM API in TensorFlow (3/7)
Erik Hallström

It would be nice if we could find a proper value for ‘truncated_backprop_length’ that ends up breaking the BasicRNNCell example due to vanishing_of_the_gradient problem and show that this is not the case for the LSTM cell. Someone has this magic number?

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.