ネットサーフィンでやさしい英語の高校、大学レベルの講義をさがしていたらこんなチャンネルをみつけたので紹介します。 Crash Courseというチャンネルです。 https://www.youtube.com/@crashcourse/playlists アメリカや世界の歴史、数学、気候とエネルギー、環境科学、数学、有機化学、生物学、心理学や政治学、経済学、英語のレトリックについての講義など、広範囲のトピックについてそれぞれ30回くらいの無料講義がアップロードされています。ただ注意してほしいのは、古いビデオもあるので最新の知見を学ぼうという人には向いていません。英語で講義する人には、講義の仕方の勉強に使うのがよいかもしれません。英語で論理的に話すとき使える言い回しとか、話の運び方などを学ぶにはやさしい講義や授業ビデオを視聴するのが参考になります。ちょっとお好きな授業をきいてみてください。けっこうわかると思いますがどうでしょう。 サンプルに疫学入門のビデオを貼り付けておきます。 Intro to Epidemiology: Crash Course Public Health #6 https://youtu.be/_luU3I03JwE
次のものは、有機化学の最終回の講義です。 Medicinal Chemistry and Penicillin Total Synthesis: Crash Course Organic Chemistry #50 https://youtu.be/qygFjt2_LG4
神経科学の入門動画の紹介です。 先日紹介したワシントン大学のSteven Brunton先生の奥さんであるBing Wen Brunton先生もワシントン大学の先生で神経科学を生物学、物理学そしてデータサイエンスの立場から研究しておられます。彼女は10歳のときにアメリカに両親とともにやってきた移民で、両親は物理学者でNASAで働いていたとのことです。彼女の簡単な自伝がこちらにあります。https://www.bingbrunton.com/bing その中に、どの道にすすもうか、どうしようかなどと悩んだ時にどうするべきかについてのアドバイスを、メンターであるカリフォルニア工科大学のGrant Jensenからもらったと書かれています。とても参考になるアドバイスだと思いますので以下に引用しておきます。 When deciding what to work on, he told me that there are three criteria that people should look for: what you’re good at, what you like to do, and what’s important for the world. He then said that most people are good with two out of three, but if I find something that fits all three, I should not hesitate and go for it. This bit of wisdom has guided my decision-making process many times. Especially when faced with walking into a position with substantial uncertainty, I try to choose options where I’ll be challenged, where I’ll learn something valuable, and where I might make a difference while spending time with fun people.
英語ですがMicrosoft Researchの動画が役立ちます。Cambridge Lab PhD Summer School というシリーズの動画です。 まずは論文の書き方の動画を二つ。 How to Write a Great Research Paperというタイトルの2本の動画です。 https://youtu.be/VK51E3gHENc
Data driven science & engineeringという本 (ケンブリッジ大学出版会発行)です。ワシントン大学のBrunton先生と同僚のNathan Kutz先生による共著の教科書で、次のサイトにhttp://databookuw.com/ 教科書に関する教材や動画のリンクが全部のっています。 物理や工学で機械学習をつかうすべての人(良くできる学部学生や修士の学生など)にピッタリの本のようです。Kindleで買っても7600円ほどの値段でちょっと高い本ですが、本の内容はすべてYouTubeに動画でみられるし、MatlabやPythonコードも無料でダウンロードできます。以下にこの本の紹介文を上のサイトからコピーしておきます。 Data-driven discovery is revolutionizing the modeling, prediction, and control of complex systems. This textbook brings together machine learning, engineering mathematics, and mathematical physics to integrate modeling and control of dynamical systems with modern methods in data science. It highlights many of the recent advances in scientific computing that enable data-driven methods to be applied to a diverse range of complex systems, such as turbulence, the brain, climate, epidemiology, finance, robotics, and autonomy. Aimed at advanced undergraduate and beginning graduate students in the engineering and physical sciences, the text presents a range of topics and methods from introductory to state of the art. Key features: —In-depth worked examples paired with comprehensive, open-source code —Concise, digestible explanations of complex concepts and their applications —Extensive online supplements include exercises, case studies, lecture videos, data, and supplementary code
この本の内容のすべてが動画でアップロードされています。上の本のサイトにリンクがあるのでそちらから観るのが簡単でおすすめです。たとえばこんな講義があります。最初の動画は特異値分解SVD(singular value decomposition)をつかった画像の圧縮の話、下の講義はカーブフィッティングと最小二乗法の話です。 https://youtu.be/QQ8vxj-9OfQ
高峰博士の生涯と桜の寄贈の話は映画化されています。「さくら さくら」という映画と「TAKAMINE」という映画の2本で、DVD化されており両方の映画を収録したDVDパッケージを購入することができます(私は2013年頃に買いました)。最初に書いたように、Amazon Prime Videoでは、どちらの映画も観ることができるので、契約している方は是非ご覧ください。予告編を並べておきます。 https://youtu.be/gM-kaVxtR7w
おなじみの英国Royal InstutionのYouTubeチャンネルにの最新の動画に、How to photograph a black hole – with Ziri Younsiという講演がアップロードされています。https://youtu.be/fGGW-kwc2n0
この動画では、ブラックホールの人類初の撮影に成功したイギリスチームのメンバーが、ブラックホールは何か、どのように見えるのか、どのように撮影するのかなどをわかりやすく解説してくれています。講演の中で映画インターステラ―の描くブラックホールに間違いがある(ブラックホールの回転にともなうドップラー効果を映画では考慮していない)という面白い話もあります。この講演を見た後、Interstellarの映画のブラックホールの描写で間違っているところはどこでしょうと、ChatGPT-4にきいてみました。 映画について詳しく教えてくれた後にこんな答えが返ってきました。結構ちゃんとした答えだと感心しました。詳しくは上の講演を聞いてみてください。 Some possible inaccuracies in the Interstellar depiction include:
1.Accretion disk brightness: The brightness and distribution of the light surrounding the black hole in Interstellar might be different from what we observed in the M87 black hole image. The accretion disk in the movie is depicted as being quite bright and uniform, while the real image shows an uneven brightness distribution.
2.Warping of light: While Interstellar did an impressive job visualizing the gravitational lensing effect of a black hole, the real image of the M87 black hole showed an even more dramatic warping of light around it. This is due to the immense gravity of the black hole bending the light from the accretion disk.
These discrepancies can be attributed to artistic liberties taken by the filmmakers and the fact that the real image of a black hole was not available during the production of Interstellar. Despite these differences, Interstellar’s Gargantua remains one of the most scientifically accurate representations of a black hole in popular media.
データ可視化や強化学習の英語無料本を3冊紹介します。初めの2冊は O’Reillyから出ている本です。 1)Hands-On Data Visualization–Interactive Storytelling from Spreadsheets to Code Jack Dougherty and Ilya Ilyankou (2023-03-07) これは紙の本は有料ですがオンラインで無料で読めます。。 https://handsondataviz.org/index.html 最新のスプレッドシート(エクセルではなくてGoogle sheetsやLibreOffice Calcそのほかのソフトを使う最新のデータ可視化の手引き書です。Google Sheets, Datawrapper, Tableau Publicなどの使い方から、Chart.js, Highcharts, Leaflet on GitHubなどでのコードの仕方など、自分のデータを可視化して皆にみせて話の流れをつくって、それを語る、そのやり方の手引き書になっているそうです。プログラミングの経験不要ということですので面白い本だと思います。
2)またデータの可視化については、こちらの本もあります。これは以前の記事で紹介した本です(末尾に該当記事をコピペしておきます)。これは、読んですぐに研究発表に使える本です。学生や研究者が研究発表するときに必須の参考書で、是非持っておきたい本ですね。 Fundamentals of Data Visualization Claus O. Wilke https://clauswilke.com/dataviz/
3)最後に強化学習の教科書も無料で読めますし、スライドやpdfをダウンロードすることもできます。 Reinforcement Learning: An Introduction written by Richard S. Sutton & Andrew G. Barto Second Edition (MIT Press, Cambridge, MA, 2018) http://incompleteideas.net/book/the-book-2nd.html
2025/3/06追記:著者二人は強化学習のパイオニアで、2024年のTuring賞を受賞しました!