Viewing profile — e_ameisen
e_ameisen
HN member- Joined
- Fri, Jun 23, 2017, 6:05 PM UTC
- HN karma
- 544
- Public activity
- 67 items
- HN profile
- View on Hacker News ↗
About e_ameisen
No profile information was provided.
Recent public activity
- story
-
comment
Comment #44131329
Hi, paper author here. This is a new tool which relies on existing introspection libraries like TransformerLens (which is similar in spirit to Garcon) to build an attribution graph…
- story
- story
- story
- story
-
comment
Comment #22805922
http://mlpowered.com/ I share practical tips about ML. I focus specifically on things that will make it easier to ship ML applications. As much as possible, I include code. Popular…
-
comment
Comment #22301426
Disclaimer: This is a book I wrote. Building Machine Learning Powered Applications walks you through building an ML application end-to-end, from product idea to a (simple) deployed…
-
comment
Comment #22273383
I'm glad you have found a workaround. Again, this is for an example script outside of the main narrative of the book, so the impact should be minimal. If pip struggles to find a sp…
-
comment
Comment #22272183
Interesting. I wasn't aware of that issue. It seems like after running activate, `pip` does point to the right location (`which pip` points to the virtualenv pip), but I'll look in…
-
comment
Comment #22271991
Sorry to hear that! Has tensorflow been your main issue? It is only used in one of the example notebooks, so you can skip that requirement without too much of an impact. If I can h…
-
comment
Comment #22261347
That’s a great question, and I’m not sure. Googling around led me to an HN thread where a commenter claims that it is TheSans (lucasfonts.com/fonts/the-sans) but I do not have a go…
-
comment
Comment #22256993
O'Reilly did organize the tech review process, where they found multiple reviewers to give detailed feedback on every part of the book. The O'Reilly staff themselves helped immense…
-
comment
Comment #22256956
I answered the next comment down the chain, but I agree with you. As framed, there is no satisfactory solution to making a question "good". Improving question quality could however…
-
comment
Comment #22256887
I'm so glad to hear you have been enjoying it!
-
comment
Comment #22256885
I do not have a slack room, but that does sound like a good idea. For now I do have an email address provided for any questions in the book, and am reachable on Twitter (mlpowered)…
-
comment
Comment #22256859
Yes, this is the approach in the book. The concept of question quality is nuanced, and does not have a clear definition. It can be easy to feel like you've solved the problem by ju…
-
comment
Comment #22256806
Not at all, choose whichever platform and medium will give you the best reading experience. I hope you find the book helpful, please reach out if you have any questions or feedback…
-
comment
Comment #22254033
It should be! The book mostly focuses on how to apply ML in practical concepts, and less about the internal workings of ML methods. I tried to explain the vast majority of ML conce…
-
comment
Comment #22249819
I recently published my first book! Writing a book has been a personal goal for the longest time, and Hacker News is the main reason I got to do so. Reading interesting posts on HN…
- story
-
story
Thank/Show HN: You Helped Me Write an O'Reilly Book
I recently published my first book! Writing a book has been a personal goal for the longest time, and Hacker News is the main reason I got to do so. Reading interesting posts on HN…
-
comment
Comment #21925664
A lot of the resources proposed in the comments focus on theoretical knowledge, or a particular sub-domain (Reinforcement Learning, or Deep Learning). I recommend a top down approa…
- story
- story