The Unreasonable Effectiveness of Meaning
Meaning hits the target missed by data: generalization and understandingA decade ago, Google’s scientists published “The Unreasonable Effectiveness of Data[i].” It focused on “natural-language-related machine learning” successes like statistical speech recognition and statistical machine translation that use large amounts of data. It preceded the best successes of deep learning which took place a
The ultimate async setup: FastAPI, SQLModel, Alembic, Pytest
FastAPI is a popular topic nowadays and I have decided to share my setup for an async web-server using this framework. Here is a short description of python packages used in the article (just to make a whole picture to save your time): Poetry (https://python-poetry.org) — is a tool for dependency management and packaging in Python. It allows you to declare the libraries your project depends on and
LlamaIndex : ChatGPTで独自のデータに対して質問するためのフレームワーク
プロンプトによる知識の外挿ChatGPTは大規模なテキストデータで学習されていますが、学習されていないデータに関しては知識が乏しいという問題があります。 例えば、特定の製品に対して質問できるチャットボットを作ろうとした場合、ChatGPTはその製品の情報を持っていないため、適切な回答ができません。 この問題は、ChatGPTのPromptに製品の情報を埋め込むという方法で解決できます。例えば、 「Aという製品でCという機能が使えないがなぜか。」 という質問の前に、 「Aという製品はBという機能とCという機能を持っており、Bという機能はCという機能と組み合わせることができない。」 という仕様書のテキストを結合して、 「Aという製品はBという機能とCという機能を持っており、Bという機能はCという機能と組み合わせることができない。Aという製品でCという機能が使えないがなぜか。」 というクエリにす
LLM’s Closing the KG Gap
I have been doing successful knowledge graph deployments with my clients for just a bit over ten years; usually with one of the big banks, but also in pharmaceutical companies and media companies. There’s a pattern to how a lot of these projects go, and that pattern makes use of a lot of standard and out-of-the-box technologies (like Semantic Web standards and RDF databases). But there’s one aspec
What I Learned as a Product Designer at Apple
In 2021 I landed my dream job. Working at Apple, the holy grail of minimalistic design, innovation and creativity. A place where misfits have a seat on the table and where bold, crazy ideas are highly encouraged. As a Product Designer, working at Apple was a life changing experience, and all I can say is that I’ll keep carrying some of its principles with me wherever I go. In the one year that I w
Mastering Retentionを読んだメモ
以下、読んだ部分の抜粋である。 © 2017 Amplitude, Inc. https://www.productanalyticsplaybook.com/ https://amplitude.com/ playbook@amplitude.com https://info.amplitude.com/rs/138-CDN-550/images/Mastering%20Retention%20JapaneseEdition.pdf また、以下からもいくつか抜粋する https://growth-marketing.jp/knowledge/define-these-two-inputs-for-your-retention-rate-formula/ ==== About Retentionリテンションを視覚化する良い方法は、N日のそれぞれのリテンションをプロットし、リテンショ ンカー
Chick-fil-Aにおけるエッジコンピューティング
Brian Chambers、Caleb Hurd、Sean Drucker、Alex Crane、Morgan McEntire、Jamie Roberts、Laura Jauch（Chick-fil-A IOT / Edgeチーム） この記事はEdge Computing at Chick-fil-Aの翻訳です。 最近の記事で、私たちはレストランというエッジロケーションでKubernetes (K8s) のためのベアメタルクラスタリングをどのように行っているかを紹介しました。私たちがよく受ける(そしてもっともな)質問は「でも、どうして？」でした。この記事で私たちはその質問に答えたいと思います。さらに興味を持った方や、文章を読むよりビデオを見る方が良い方は、 QConNY 2018でのBrianとCalebのプレゼンテーションをご覧ください。 (Kubernetesを含む新しいコンテナオ
How Machine Learning Became Useful
This blog is cross posted on the Aqueduct blog. Artificial intelligence and machine learning have become a critical piece of every aspect of life today. Yet 15 years ago, machine learning was a much smaller research discipline. How did a field born out of mathematics and theoretical computer science join forces with rapid innovation in data and computer systems to change the modern world? This is
How to win a Kaggle competition in Data Science (via Coursera): part 1/5
Source: CourseraThese are my notes from the 5-weeks course on Coursera, as taught by a team of data scientists and Kaggle GrandMasters. ## Week 1 ##by Alexander Guschin, GM #5, Yandex, lecturer at MIPT Mikhail Trofimo, PhD student at CCAS Learning ObjectivesDescribe competition mechanicsCompare real life applications and competitionsSummarize reasons to participate in data science competitionsDesc
Presenting Code Using Jupyter Notebook Slides
When you make a slide presentation, there are a few programs you likely think of: Microsoft PowerPoint, Google Slides, Prezi (just kidding). PPT and Slides are great applications, to be sure. They offer tons of formatting and style options and integrate well with other software developed by Microsoft and Google, respectively. But there is another great program for making slides, and it is especial
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Mike Hearn – Medium
Data Agents
Summarize YouTube videos with LlamaIndex and GPT
Auto Generating Google Forms
Ethics + Data Science
What is Google Trends data — and what does it mean?
Understanding product attributes for shoppers
Pin2Interest: A scalable system for content classification
Interest Taxonomy: A knowledge graph management system for content understanding at Pinterest
個人開発におすすめな Firebase Extensions