
機械学習関連で勉強したことをゆるく発信していく podcast です。 Show notes は github.com/yoheikikuta/hikifune.fm です。
| Publishes | Twice monthly | Episodes | 20 | Founded | 5 years ago |
|---|---|---|---|---|---|
| Language | Category | Technology | |||

曳舟から引っ越すので hikifunefm というタイトルでの配信が最後ということで、ゲストを呼んでこれまでを振り返る雑談回です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/main/ep/018.md です。
発表者:@yohei_kikuta, @karino2012
パラメタ最適化のフレームワークである Optuna について、committer とワイワイ話す回です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/main/ep/017.md です。
発表者:@himkt, @yohei_kikuta
アミノ酸配列からタンパク質の立体構造を予測する問題において文字通り桁違いの性能を示した AlphaFold(2) に関して、タンパク質研究のプロとわいわい議論する回です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/main/ep/016.md です。
発表者:@Ag_smith, @yohei_kikuta
00:00:38~ ゲスト自己紹介と論文についての簡単な所感
00:08:48~ タンパク質の立体構... more
技術的内容はないです。hikifunefm は不定期配信にするという報告です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/master/ep/015_5.md です。
発表者:@yohei_kikuta
pre-trained T5 で downstream タスクを解く時にタスクを記述する prompt token のみを学習して高い精度(巨大モデルではモデル全体を再学習するのとほぼ同等)を達成する prompt tuning の論文を紹介する回です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/master/ep/015.md です。
発表者:@yohei_kikuta
ディープラーニングの量子化学への応用である PauliNet の論文を読んだという会。あまり理解してないのでそれっぽいことを雰囲気で述べる会です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/master/ep/014.md です。
発表者:@yohei_kikuta
DALL·E の理解に向けて part 3 としてついに公開された DALL·E の論文を読む回。論文は学習に関する技術的内容が多いですが、それらにはあまり触れずに DALL·E のモデルがどういう構造なのかという観点で話をしています。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/master/ep/013.md です。
発表者:@yohei_kikuta
聞き手:@smochi_pub
masa_kazama が興味を持って勉強している計算社会科学についてあれこれと話す回です。
Show notes は github.com/yoheikikuta/hikifune.fm/blob/master/ep/012.md です。
発表者:@masa_kazama
聞き手:@yohei_kikuta









Listeners, social reach, demographics and more for this podcast.
| Gender Skew | Location | Interests | |||
|---|---|---|---|---|---|
| Professions | Age Range | Household Income | |||
| Social Media Reach | |||||
Rephonic provides a wide range of podcast stats for hikifune.fm. We scanned the web and collated all of the information that we could find in our comprehensive podcast database. See how many people listen to hikifune.fm and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.
Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for hikifune.fm, including podcast download numbers and subscriber numbers, so you can make better decisions about which podcasts to sponsor or be a guest on. You will need to upgrade your account to access this premium data.
Rephonic provides comprehensive predictive audience data for hikifune.fm, including gender skew, age, country, political leaning, income, professions, education level, and interests. You can access these listener demographics by upgrading your account.
To see how many followers or subscribers hikifune.fm has on Spotify and other platforms such as Castbox and Podcast Addict, simply upgrade your account. You'll also find viewership figures for their YouTube channel if they have one.
These podcasts share a similar audience with hikifune.fm:
1. Rebuild
hikifune.fm launched 5 years ago and published 20 episodes to date. You can find more information about this podcast including rankings, audience demographics and engagement in our podcast database.
Our systems regularly scour the web to find email addresses and social media links for this podcast. We scanned the web and collated all of the contact information that we could find in our podcast database. But in the unlikely event that you can't find what you're looking for, our concierge service lets you request our research team to source better contacts for you.
Rephonic pulls ratings and reviews for hikifune.fm from multiple sources, including Spotify, Apple Podcasts, Castbox, and Podcast Addict.
View all the reviews in one place instead of visiting each platform individually and use this information to decide if a show is worth pitching or not.
Rephonic provides full transcripts for episodes of hikifune.fm. Search within each transcript for your keywords, whether they be topics, brands or people, and figure out if it's worth pitching as a guest or sponsor. You can even set-up alerts to get notified when your keywords are mentioned.