machine-learning-book
machine-learning-book copied to clipboard
rasbt
Code Repository for Machine Learning with PyTorch and Scikit-Learn
Dear Prof. Sebastian Raschka, I published a [blog](https://jackli777.github.io/3b1b-some2-2022-/) with an accompanying [3D interactive website](https://jackli777.github.io/visualizing-ai/) based on your published [notebook](https://github.com/rasbt/machine-learning-book/blob/main/ch16/ch16-part1-self-attention.ipynb), to visualize the inner working of Transformer, hope you can check...
In page 477. The formula for spatial dimension of output feature map $$ o = \left [ \frac{n + 2p -m}{s} \right ] + 1 $$ should be corrected with...
In Page 458, In the following paragraph at the bottom of page, Consider the following two cases: * Compute the output size for an input vector of size 10 with...
In page 361, MSE Loss equation missing index i in the first summation. > $$ L \big ( \mathbf{W}, \mathbf{b} \big ) = \frac{1}{n} \sum_{1}^{n} \frac{1}{t} \sum_{j=1}^{t} \big( y_{j}^{[i]} -...
I ran across another couple of typos in the book. The Jupyter notebook with the data is correct. Chapter 15, page 508, 2nd code block, line 12 is missing the...
Hi Sebastian, There is the description of the batch and layer normalization (including the picture) on the page 560: "While **layer** normalization is traditionally performed across all elements in a...
> Suggestion : I would recommend and suggest that the author do a flowchart or a diagram for all steps from chapter 1 to 6 for each Machine learning algorithm...
actually, I am not sure why I wasn't computing it with loss = np.sum((onehot_targets - probas)**2) (instead of mean) in the loop and then using mse = mse/num_examples instead of...