iamtrask/Grokking-Deep-Learning

Issues

• chap8:layer_1_delta *= dropout_mask

  #68 opened 2 months ago by mmdxl-dcy
  0

• chapter 10, is the `for row_start in range(layer_0.shape[1]-kernel_rows)` correct?

  #43 opened 5 years ago by DawnEve
  2

• Chapter 8 examples, why do they all turn label into one_hot_labels

  #63 opened 2 years ago by qiulang
  3

• Help Please

  #66 opened 9 months ago by jumpbackjack65
  2

• Chapter 13 - I have a problem trying to implement the autograd in a simple linear regresion

  #46 opened a year ago by HectorPulido
  1

• Something wrong with the code in chapter 10

  #65 opened a year ago by Jason-XII
  0

• Chapter 4 - How is weight_delta computed ?

  #49 opened 4 years ago
  6

• License

  #51 opened 4 years ago by bennytheshap
  1

• chapter 6

  #62 opened 2 years ago by varunponda
  0

• 2nd edition?

  #61 opened 2 years ago by austinmw
  0

• Chapter 6 - Array in array vs use vector

  #58 opened 3 years ago by oleg-tgn
  1

• Mistake in Ch3. code

  #60 opened 2 years ago by ahussein1194
  0

• Chapter 6 - layer_1_delta

  #59 opened 3 years ago by doudou-h
  0

• Ch11 Predicting Movie Reviews - error in back propagation code

  #50 opened 4 years ago by harpreetmann24
  9

• chapter8 relu2deriv

  #9 opened 6 years ago by leeivan1007
  3

• Inactive Activation gradients

  #56 opened 4 years ago by Seabrand
  1

• Chap8: the way of mini-batch gradient descent updating weights

  #31 opened 5 years ago by shenxiangzhuang
  6

• Authorization to re-implement in another language

  #57 opened 4 years ago by aPixelInSpace
  2

• ch 10 kernel weight update typo

  #55 opened 4 years ago by AlexCalderwood
  0

• lots of mistakes and illogical ordering? is this a pre-script?

  #53 opened 4 years ago by Benitodilorenzo
  0

• Missed variable

  #52 opened 4 years ago by ljapkin-roman
  0

• Chapter 6: layer_2_delta calculation

  #37 opened 5 years ago by Vaticinator
  2

• what is the size of the dictionary in chapter 14

  #48 opened 4 years ago by RomanGhost
  0

• Page 128, Ch. 6

  #36 opened 5 years ago by ncfausti
  1

• NameError in Chapter 4 notebook

  #45 opened 5 years ago by deepaksuresh
  0

• small mistake in Chapter 15

  #33 opened 5 years ago by moFang222
  1

• Chapter 15 small issue in train

  #40 opened 5 years ago by logancyang
  2

• Chapter 8: Batch gradient descent. Wrong alpha value

  #42 opened 5 years ago by cesarab
  0

• Question about delta in chapter 5

  #41 opened 5 years ago by BoxOfCereal
  0

• Chapter 10: CNN

  #39 opened 5 years ago by ariG23498
  1

• Chapter-4-page-53

  #38 opened 5 years ago by danarchos
  0

• chapter 5-bugfix

  #34 opened 5 years ago by rezabojnordi
  0

• Chapter 5: weight_deltas calculation in case of multiple inputs and multiple outputs

  #23 opened 5 years ago by dimchansky
  3

• Ending Notes Suggestions

  #30 opened 5 years ago by prateekrastogi
  0

• small mistakes in Chapter 3

  #8 opened 6 years ago by paulweill
  1

• Chapter 15, section "Secure Aggregation" -- extra deepcopy?

  #28 opened 5 years ago by alexvoronov
  0

• Chapter 13 - Passing all ones tensors for backprop

  #27 opened 5 years ago by danielepaliotta
  0

• Chapter 5: Gradient Descent Learning with Multiple Inputs

  #25 opened 5 years ago by sergeda
  0

• Chapter13 - Intro to Automatic Differentiation - index_select_indices variable was never created previous to use

  #24 opened 5 years ago by danieljoserodriguez
  1

• Please add a LICENSE + A Rust Implementation

  #14 opened 6 years ago by suyash
  1

• Chapter 11: code formatting is broken

  #21 opened 5 years ago by christophboesch
  8

• Chapter 13. P.244: Why the backprop is different for "mul"?

  #19 opened 6 years ago by davidjones1
  1

• Weight updates in rnn

  #18 opened 6 years ago by koulritesh98
  0

• Chapter 10

  #17 opened 6 years ago by koulritesh98
  0

• NameError: name 'weight_deltas' is not defined in Chapter5.ipynb "Gradient Descent Learning with Multiple Inputs"

  #3 opened 6 years ago by c-r-p
  1

• Just a suggestion

  #7 opened 6 years ago by sam-thecoder
  1

• Activate layer 2 output using Relu()?

  #15 opened 6 years ago by michaelmegliola
  1

• Repeated iterations

  #16 opened 6 years ago by naruto678
  2

• Error: Learning rate value (Section 4.6)

  #11 opened 6 years ago by mtn
  1

• Error: Hot and cold learning conditional (Section 4.6)

  #12 opened 6 years ago by mtn
  1