Grokking-Deep-Learning
Grokking-Deep-Learning copied to clipboard
iamtrask
this repository accompanies the book "Grokking Deep Learning"
On pg 183 (also chapter10 - Intro to convolutional Neural Networks - learning edges and corners.ipynb), I believe that `kernels -= alpha * k_update` should read `kernels += alpha *...
Hey as i see there a actually many mistakes in the book. I found several parts where I just get confused and have to guess or rely on trying. Pls...
In chapter 8 , after adding Batch gradient descent you missed a variable "images"
Section "Backpropagation in Code": There is: `layer_2_delta = (walk_vs_stop[i:i+1] - layer_2)` I belive it should be: `layer_2_delta = (layer_2 - walk_vs_stop[i:i+1])`
I have the size len(vocab)=62. I think it small for 512.
Where does .14 come from? `layer_2_delta=(layer_2-walk_stop[0:1])` `walk_stop = np.array([[ 1, 1, 0, 0]]).T` Wouldn't this just be -.02 - 1 === -1.02?
I tried this, mi input size is 1, 1000 and my output size is 1, 100 ``` import random as r x = np.array(range(1000)) y = x * 12 +...
In the first cell, the variable `weight_deltas` is not defined. The call happens here ``` for i in range(len(weights)): weights[i] -= alpha * weight_deltas[i] ```
Adding calculation to derive weight_deltas array from ele_mul function with delta and input as parameters
