Viewing profile — amatsukawa
amatsukawa
HN member- Joined
- Tue, Sep 27, 2011, 7:43 PM UTC
- HN karma
- 50
- Public activity
- 20 items
- HN profile
- View on Hacker News ↗
About amatsukawa
No profile information was provided.
Recent public activity
-
comment
Comment #26452318
Dask is popular for this purpose. No memory compression, but supports disk spillage as well as distributed dataframes.
-
comment
Comment #13817537
It still scales O(N^2) in terms of computation though right?
-
comment
Comment #13817529
Let me make sure I understand: rather than using gates, each step explicitly takes a weight average of all past steps using attention. What is the training speed of this network? C…
-
comment
Comment #13538689
Rigor is there. I'm now working in the ML/AI research division of big-4, all I needed (and all hiring teams needed to see on my resume) were a couple of these classes (with good in…
-
comment
Comment #13538675
I've taken a couple on this list (employer paid as a perk, no way I would pay this price out of pocket) and I can attest it is 100x more worthwhile than Coursera MOOC. You actually…
-
comment
Comment #13538648
Are you talking about guaranteed advancement into a real degree? That indeed does not exist, but if you do well on these, you are probably pretty eligible for their part-time MS pr…
-
comment
Comment #9843053
2 cents from someone who took CS61A in scheme and had a hand in creating the new python version of the course and subsequently was a TA for the class for a few semesters on this de…
-
comment
Comment #6537512
No, I believe he actually meant LSA = latent semantic analysis, which is an algorithm used to extract topics. I am also curious about how the NLP/ML parts are implemented, as it's …
-
comment
Comment #6119761
I don't really know Go except for like 5 min of reading up on its syntax, so I could be wrong, but this assertion that it was not obvious how to write to a file in the documentatio…
-
comment
Comment #5494734
I'm not sure I agree with the sentiment that people who code in dynamic languages don't think about signatures and types. If anything, people who write in dynamic languages think a…
-
comment
Comment #5354398
This is probably easier for a computer to crack than a well-built traditional CAPTCHA. Recognizing a pre-defined small set of images (the chess pieces) and performing a search for …
-
comment
Comment #4349098
Took this class at Berkeley last semester. Hard but very good, as long as you have the right mathematical background. Think graduate level math/stats and not "I took the ML course …
-
comment
Comment #4265044
This looks awesome. It would be cool if you could build a community around this. I wish I could not only post with this tool, but also read what others are writing. While someone m…
-
comment
Comment #4162781
Pretty season's Vim user here. This editor looks awesome, and I would love to give it a whirl, but I feel like I can't switch without these plugins. I'm sure they exist, if someone…
-
comment
Comment #4005377
They should mount this inside a keyboard, I don't want an extra dongle randomly lying on my table. On a completely different note, though, I wonder what the range on these things i…
-
story
Ask HN: Can we get anonymous data of HN?
I would love to build a recommendation engine for HN, but I don't know of any available data. Is there any way we can get some anonymized logs of ids, links, upvotes, timestamp, et…
-
comment
Comment #3965420
Same, expected some good counter arguments to the article mentioned in the post. Instead, it reinforced my every stereotype about business people.
-
comment
Comment #3718776
As someone who took the Scheme version and is now teaching the Python version, there are without a doubt aspects of the course I miss. The old Scheme course just had a kind of eleg…
- story
-
comment
Comment #3144743
(also a TA for the course) I took this class while it was still taught in Scheme, and I loved it. Now I'm teaching it in Python. I am also sad to see Scheme go, but I think we gain…