diff --git a/README.md b/README.md
index 5330914..dc2c035 100644
--- a/README.md
+++ b/README.md
@@ -4,6 +4,7 @@
Download PDF •
About •
+ Errata •
@@ -112,3 +113,65 @@ Shlomo Kashani, Author of the book _Deep Learning Interviews_ www.interviews.ai:
+
+# Errata (May not be up to date)
+
+## **I would like to solicit corrections, criticisms, and suggestions from students and other readers. Although I have tried to eliminate errors over the multi year process of writing and revising this text, a few undoubtedly remain. In particular, some typographical infelicities will no doubt find their way into the final version.** **I hope you will forgive them.**
+## ***Minor corrections are not included.***
+
+Thank you to all the readers who pointed out these issues.
+**Errata for the version** **03/12/2020** **printing and reflected in the online version:**
+
+1. Question number **PRB-267 -CH.PRB- 8.91** was removed due to lack of clarity
+2. Question number **PRB-115 - CH.PRB- 5.16** was removed due to lack of clarity
+
+**Errata for the version** **05/12/2020** **printing and reflected in the online version:**
+
+1. Page 230, Question number **PRB-178** amend “startified scross validation“ TO “stratified cross validation.“
+2. Page 231, Question number **PRB-181** added a ” .“ after data-folds
+3. Page 231, Question number **PRB-191** amend “an” to “a”
+4. Page 234, Question number **PRB-192** “in” repeated twice
+5. Page 236, Question number **PRB-194 amend** “approached” to “approaches“, “arr” to “arr001”
+6. Page 247, Question number **PRB-210 amend** “an” to “a”
+7. Page 258, Question number **PRB-227 amend** “A confusion metrics” to “A confusion matrix”
+8. Page 271, Question number **PRB-240 amend** “MaxPool2D(4,4,)” to “MaxPool2D(4,4)”
+9. Page 273, Question number **PRB-243 amend** “identity” to “identify”
+10. Page 281, Question number **PRB-254 amend** “suggest” to “suggests”
+11. Page 283, Question number **PRB-256** “happening” misspelled
+12. Page 286, “L1, L2” amended to “Norms”
+13. Page 288, Question number **SOL-184** **amend** “the full” to “is the full”
+14. Page 298, Question number **SOL-208** **amend** “ou1” to “out”
+15. Page 319, Question number **SOL-240** **amend** “torch.Size([1, 32, 222, 222]).” to “torch.size([1, 32, 222, 222]).“
+16. Page 283, Question number **PRB-256** “happening” was misspelled
+
+**Errata for the version** **07/12/2020** **printing and reflected in the online version:**
+
+1. Page 187, Question number **PRB-140** two missing plots (6.3, 6.4) which did not render correctly on the print version
+
+
+
+6.3
+
+
+
+
+6.4
+**Errata for the version** **09/21/2020** **printing and reflected in the online version:**
+
+1. Page 34, Solution number **SOL-19** , 0.21886 should be 0.21305 and 0.21886 ± 1.95 × 0.21886 should be **0.21305** ± 1.95 × 0.21886
+2. Page 36-7, Solution number **SOL-21** ,4.8792/0.0258 = **189.116** and not 57.3 and pi(33) = 0.01748 and not pi(33) = **0.211868**.
+3. Page 49, **PRB-47** “What is the probability that the expert is a **monkey**“ should be “What is the probability that the expert is a **human**”
+
+**Errata for the version** **09/22/2020** **printing and reflected in the online version:**
+
+1. Page 73, Solution number **SOL-56** should read ”The Hessian is generated by **differentiating**”
+2. Page 57, Problem number **PRB-65** should read ”**two** neurons”
+
+**Errata for the version** **09/24/2020** **printing and reflected in the online version:**
+
+1. Page 78, Solution number **SOL-64** , the OnOffLayer is off only if at least 150 out of 200 neurons are off. Therefore, this may be represented as a Binomial distribution and the probability for the layer to be off is :
+
+
+
+
+