Hacker News Reader

zhenghaozon How to Use AVX512 in Golang

Thanks, @gnabgib. Your comment is very insightful and reminds me of my mentor correcting my academic paper. The post introduces the basic idea of using AVX512 in Go by writing C codes. There are mistakes and many details are omitted. A complete example is https://github.com/gorse-io/gorse/tree/master/base/floats

zhenghaozon How to Use AVX512 in Golang

It is a pity that CGO isn't in the final benchmark. >_<

zhenghaozon How to Use AVX512 in Golang

For someone experts assembly, avo is a better tool to write assembly in hand.

zhenghaozon How to Use AVX512 in Golang

I am the author and I am really regret about this title. I think a better title should be "How to Use AVX512 in Golang via the C Compiler" :O

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

I think NLP technology should be used for your project :) I plan to integrate Gorse with NLP, but it might take years to implement it.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Thanks for your insight. In the recommendation scenario that freshness is important, real-time recommendation is more in demand.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

To be honest, popular items have more chance to be recommended, and it is hard to avoid. Popular items have higher probability to be liked. In addition, popular items have more data collected, it helps to locate potential users.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

The reason to use real time recommendations is there are contextual informations. However, Gorse doesn't use contextual informations, it doesn't handle real time recommendations yet.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Once I collect context aware dataset, context aware recommenders could be implemented :)

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Thanks. I will take a look at it :)

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Graph databases are good at locating related items/users, which is useful for recommender systems :)

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

I will try it :)

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

I list papers here: https://docs.gorse.io/ch01-02-recommend.html#online-evaluati...

I will introduce algorithms briefly in documents in the future :)

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Yeah, I know "Gource", another cool project. :D

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Good idea! But before that, we have to take a look at GDPR :D

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

The problem is how to utilize these signals. The annoying thing is we can't solve these issues if we are not in this situation. So, feedbacks from Gorse users are important.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Your consideration is absolutely right. The abstractions in Gorse do lose lots of informations. Prior knowedges, contextual informations is important to further improve recommender systems.

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

Thanks for your advice

zhenghaozon Show HN: Gorse – An Out-of-the-box open-source Recommender System

There are no explicit negative feedback yet. When a item is seen by a user, the read event is recorded. If this user likes this item, the positive feedback is recorded. It seems a natural way to track user's preference. I will try to add explicit negative feedback if someone really need it.