Aurélien Geron

Hi Chris, Thanks for clarifying, I understand your point and I really appreciate your feedback. I agree that my naive approach is too naive when predicting 10 steps ahead: it...

Awesome response, Chris, thanks so much. I had a sum of sine waves and yet I didn't think of the Fourier transform... silly me! :) I'll give this a try.

Hi @Kirushikesh , Thanks for your kind words and your interesting question. Scikit-Learn's source code is actually quite readable, that's often where I get the best answer to my questions,...

Thanks for this great discussion, @liganega and @vi3itor , I really appreciate it. I'm currently working on improving the installation instructions. I don't use Windows, so this thread will definitely...

Hi @derycck , Thanks for the suggestion! Would you like to submit a PR? If not, I can do it, as you wish.

Thanks for the information and for your suggestion, that's very helpful. I'll look into this asap.

Hi @BuggieCoder , Thanks for your feedback. It looks like the official installation instructions for TensorFlow Serving currently do not work on Google Colab, but luckily the workaround proposed by...

Thanks for your feedback @atonkamanda, that's a very interesting remark. I think the timeline looks like this: * 1940s: researchers create the first artificial neuron and they use a step...

Hi @michaelmiscanuk , The `training` argument is automatically set to `True` by Keras during training, you don't need to do anything. And it's automatically left to the default value otherwise....

Note: if you want to be sure that `training` is set to `True`, you can use `tf.print()` to print a log message, for example: ```python class AddGaussianNoise(keras.layers.Layer): def __init__(self, stddev,...