• Post Reply Bookmark Topic Watch Topic
  • New Topic
programming forums Java Mobile Certification Databases Caching Books Engineering Micro Controllers OS Languages Paradigms IDEs Build Tools Frameworks Application Servers Open Source This Site Careers Other all forums
this forum made possible by our volunteer staff, including ...
Marshals:
  • Campbell Ritchie
  • Paul Clapham
  • Ron McLeod
  • Liutauras Vilda
  • Bear Bibeault
Sheriffs:
  • Jeanne Boyarsky
  • Tim Cooke
  • Devaka Cooray
Saloon Keepers:
  • Tim Moores
  • Tim Holloway
  • Piet Souris
  • salvin francis
  • Stephan van Hulst
Bartenders:
  • Frits Walraven
  • Carey Brown
  • Jj Roberts

Tensor Flow 2.0 Promo

 
Ranch Hand
Posts: 36
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
I am new to AI. Is this a good place to start? If not, can you recommend good starting sources to augment this book?
I have Google Cloud Account, AWS. I have dabbled with the skills.
I'll check other answers for the practical uses so I don't go over my one allowable question.
Thanks -
Thomas Zink
 
Author
Posts: 24
2
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
Hey Thomas,

If you're new to AI, I would recommend first starting with a simple models and usecases. Why I'm saying this is, when jumping directly to deep learning, it's quite easy to lose appreciation for the full ML workflow. I.e.

+ EDA
+ Data cleaning
+ Feature engineering
+ Modeling
+ Model evaluation
+ Model interpretation

I try to touch on every one of these topics as much as I can. But due to the nature of deep learning, feature engineering is almost non-existent and even data cleaning is not performed (especially in computer vision). And some don't even think anything beyond once they get to a good accuracy! That's quite wrong because we don't know if the model learned good features if we do not interpret the model.

Unfortunately I don't really have a recommendation in my mind, as I haven't come across a book that covers the whole process end to end as well as goes at a reasonable pace. You can try https://www.manning.com/books/machine-learning-in-action. But I cannot personally endorse this as I haven't read this. If possible best way to do would be to do a course (even a small one) at a university. This way you get face-to-face interaction and the benefit of a well developed syllabus.

Good luck on your journey!
 
Don't get me started about those stupid light bulbs.
reply
    Bookmark Topic Watch Topic
  • New Topic