New answers tagged

0

Okay, the solution is actually pretty simple: I just had to modify the dense = Dense(units=1)(lstm) part and replace it with dense = Dense(units=output_length)(lstm) to make this work. Now the length of the input sequence is 60 timesteps with a dimensionality of 19 and the output sequence will be of 20 timesteps with a dimensionality of 1.


0

The logarithm you take is probably for the wrong basis. The log-exp-trick relies on 'changing nothing' in a mathematical meaning. For example: $$ \Leftrightarrow \log_{10}(10^4) = 4 \\ 10^{log_{10}(10^4)} = 10000 $$ But this only works with the right base: $$a^{log_{a}(b)} = b$$ If you take 2 to the power of something your logarithm should be with respect to ...


0

In keras.layers.LSTM(units, activation='tanh', ....), the units refers to the dimensionality or length of the hidden state or the length of the activation vector passed on the next LSTM cell/unit - the next LSTM cell/unit is the "green picture above with the gates etc from http://colah.github.io/posts/2015-08-Understanding-LSTMs/ The next LSTM cell/unit ...


1

I finally manage to figure out the reason of weighting KL divergence in VAE. It is more about the normalized constant of the distribution modeled the target variable. Here, I am going to present some output distributions we often use. Most of the notation will follow the book "Pattern recognitions and Machine learning". Linear regression (...


3

The procedure presented in the paper seems to be slightly different from the one above. In the paper the authors make an ansatz that explicitely fulfills the initial conditions. For a second order differential equation of the form $$ \Psi''(t)=f(t,\Psi(t),\Psi'(t)) $$ with $\Psi(0)=A$ and $\Psi'(0)=B$ they suggest to use (see section 3.1 and specifically ...


0

Apparently, Tensorflow computes the average of the negative log likelihood terms rather than their sum: import tensorflow as tf def categorical_ce(y, logit, reduce_mean=True): cce = \ -tf.reduce_sum( tf.math.log( tf.nn.softmax(logit) ) * tf.one_hot( tf.cast(y, tf.int32), ...


1

You won't experience a "spiral" in the real world. But it is one of the more complex yet easy to visualize non-linear datasets. The playground in your question is for building intuition with neural networks. The other answers gave solutions that work but in my opinion miss the point of what can be learned here. In the real world, most non-linear ...


Top 50 recent answers are included