Aurélien Geron

Ah merci beaucoup, je vais remonter cette erreur à Dunod, qui est en charge de la traduction. 👍

Hi @panghucui , Thanks for your question. I chose 49% and 54% because they were the first round numbers more than 2% away from the real female ratio. I could...

Hi @YecanLee , Thanks for your feedback. I cannot reproduce this error. When in doubt, you can always run the code using [Google Colab](https://colab.research.google.com/). For example, the notebook for chapter...

Hi @KonFey, Yes, you are 100% correct. Hash functions typically produce hashes that look pretty close to random, roughly following a uniform distribution over the range of possible values. This...

Hi @Barleysack , Thanks for your feedback. Regarding the first issue, indeed the latest version of TensorFlow is not compatible with NumPy 1.19 (as of May 2021, this will change...

Hi @sinharahul , Thanks for your feedback, and my apologies for the late response. I've updated the Dockerfile, and I successfully built [ageron/handson-ml3](https://hub.docker.com/repository/docker/ageron/handson-ml3). Could you please give it another try?

Hi @diegoug, Sorry for the late reply. Reinforcement Learning is used to train an agent to optimize its rewards as it interacts with an environment. In other words, RL is...

Thanks for your suggestion @eisthf. Preprocessing layers did not exist yet when I wrote the second edition, they were just rough specs so I had to do my best to...

The goal of this function is to shuffle the instances and put them in the test set (True) or train set (False) in a stable way (i.e., deterministic), based on...

Hi, thanks for your feedback. It looks like the code you are running is slightly different from the one in the notebook. You are using lowercase names like `x_test` and...