並び順

ブックマーク数

期間指定

  • から
  • まで

1 - 12 件 / 12件

新着順 人気順

interpretabilityの検索結果1 - 12 件 / 12件

  • Language Interpretability Tool (LIT) の紹介 - 機械学習 Memo φ(・ω・ )

    概要 Google Researchが、言語解釈ツール Language Interpretability Tool (LIT) を紹介する論文を出しました。NLPモデルが期待どおりに動作しない場合に、何が問題かを解明するために役立つツールだと記載されていて、便利そうだと思い試しに動かしてみたので、LITの簡単な紹介を記載します。 [2008.05122] The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models 概要 LITとは インストール LITの起動 インスタンスの起動 quickstart_sst_demo pretrained_lm_demo インスタンス起動用のスクリプト作成 Datasetクラス Modelクラス 公式ドキュメン

      Language Interpretability Tool (LIT) の紹介 - 機械学習 Memo φ(・ω・ )
    • GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

      Modern LLMs encode concepts by superimposing multiple features into the same neurons and then interpeting them by taking into account the linear superposition of all neurons in a layer. This concept of giving each neuron multiple interpretable meanings they activate depending on the context of other neuron activations is called superposition. Sparse Autoencoders (SAEs) are models that are inserted

        GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
      • GitHub - PAIR-code/lit: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

        The Learning Interpretability Tool (🔥LIT, formerly known as the Language Interpretability Tool) is a visual, interactive ML model-understanding tool that supports text, image, and tabular data. It can be run as a standalone server, or inside of notebook environments such as Colab, Jupyter, and Google Cloud Vertex AI notebooks. LIT is built to answer questions such as: What kind of examples does m

          GitHub - PAIR-code/lit: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
        • GitHub - MAIF/shapash: 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

          Shapash is a Python library designed to make machine learning interpretable and comprehensible for everyone. It offers various visualizations with clear and explicit labels that are easily understood by all. With Shapash, you can generate a Webapp that simplifies the comprehension of interactions between the model's features, and allows seamless navigation between local and global explainability.

            GitHub - MAIF/shapash: 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
          • Learning Interpretability Tool

            The Learning Interpretability Tool (🔥LIT) is a visual, interactive ML model-understanding tool that supports text, image, and tabular data. The Learning Interpretability Tool (🔥LIT) is for researchers and practitioners looking to understand NLP model behavior through a visual, interactive, and extensible tool. Use LIT to ask and answer questions like: What kind of examples does my model perform

            • Interpretability in Machine Learning: An Overview

              This essay provides a broad overview of the sub-field of machine learning interpretability. While not exhaustive, my goal is to review conceptual frameworks, existing research, and future directions. I follow the categorizations used in Lipton et al.'s Mythos of Model Interpretability, which I think is the best paper for understanding the different definitions of interpretability. We'll go over ma

                Interpretability in Machine Learning: An Overview
              • AIの"心"を読む技術?Anthropic ダリオCEOが語る『Mechanistic Interpretability』の全貌と未来への緊急警報|Kyutaro

                AIの"心"を読む技術?Anthropic ダリオCEOが語る『Mechanistic Interpretability』の全貌と未来への緊急警報 皆さんは、ChatGPTやClaudeのようなAIアシスタントと話していて、こんな風に思ったことはありませんか? 「うーん、なんで今この言葉を選んだんだろう?」 「時々、すごく的確なのに、たまに変な間違いをするのはなぜ?」 AIは日に日に賢くなり、私たちの仕事や生活に欠かせないパートナーになりつつあります。でも、その一方で、私たちは彼らの「頭の中」で何が起きているのか、実はほとんど理解できていません。 まるで、ものすごく優秀な同僚が隣にいるけれど、その人がどうやって考えて結論を出しているのか、全く教えてくれないような状態です。 今回は、この大きな謎に挑む「解釈可能性(Interpretability)」という、今AI業界で最もホットで重要な研究

                  AIの"心"を読む技術?Anthropic ダリオCEOが語る『Mechanistic Interpretability』の全貌と未来への緊急警報|Kyutaro
                • GitHub - fraware/leanverifier: Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.

                  You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

                    GitHub - fraware/leanverifier: Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.
                  • Dario Amodei — The Urgency of Interpretability

                    In the decade that I have been working on AI, I’ve watched it grow from a tiny academic field to arguably the most important economic and geopolitical issue in the world.  In all that time, perhaps the most important lesson I’ve learned is this: the progress of the underlying technology is inexorable, driven by forces too powerful to stop, but the way in which it happens—the order in which things

                      Dario Amodei — The Urgency of Interpretability
                    • 【レポート】Interpretability and explainability in machine learning | DevelopersIO

                      【レポート】Interpretability and explainability in machine learning こんにちは、Mr.Moです。 本エントリーは re:Invent 2020で行われたセッション "Interpretability and explainability in machine learning" のレポートです。 セッション概要 As machine learning (ML) becomes increasingly ubiquitous across many industries and applications, it is also becoming difficult to understand the rationale behind the results of ML models. Understanding how ML model

                        【レポート】Interpretability and explainability in machine learning | DevelopersIO
                      • Windows10環境でLanguage Interpretability Tool (LIT)を実行(1.環境構築編) - Qiita

                        Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? Google ResearchがNLPモデルの理解と可視化をするプラットフォームLanguage Interpretability Tool (LIT)をオープンソース化しました。試しに動かしてみたいと思います。 全3記事を予定しています。 1. Windows10環境でLanguage Interpretability Tool (LIT)を実行(1.環境構築編)【本記事】 2. Windows10環境でLanguage Interpretability Tool (LIT)を実行(2.機能確認編) 3. Windows10環境でLa

                          Windows10環境でLanguage Interpretability Tool (LIT)を実行(1.環境構築編) - Qiita
                        • 機械学習における解釈可能性 (Interpretability) と説明可能性 (Explainability) のニュアンスの違い

                          機械学習における解釈可能性 (Interpretability) と説明可能性 (Explainability) のニュアンスの違い 混同して用いられる2つの概念だが、厳密には以下のようなニュアンスの違いがある(と個人的に思っている)。何か意見等あればコメントください! 解釈可能性 (Interpretability) (しばしばブラックボックスである)機械学習モデルに対して、そのモデルが予測を返す仕組み(そのもの) を明らかにできること。 説明可能性 (Explainability) 機械学習モデルの予測に対して、なぜその予測を返したのか説明できること。 解釈可能性が高いからといって、説明可能性が高いとは限らない 線形回帰や決定木のような解釈可能性の高い手法では、モデルの予測に寄与するメカニズムである"特徴量"を計算することができる。しかしながら、特徴量の大きな変数を複数持つ入力をモデル

                            機械学習における解釈可能性 (Interpretability) と説明可能性 (Explainability) のニュアンスの違い
                          1