説明可能なAI:深層学習の解釈・説明・視覚化の最前線<br>Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (Lecture Notes in Artificial Intelligence)

個数:
電子版価格
¥17,223
  • 電子版あり

説明可能なAI:深層学習の解釈・説明・視覚化の最前線
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (Lecture Notes in Artificial Intelligence)

  • オンデマンド(OD/POD)版です。キャンセルは承れません。
  • 【入荷遅延について】
    世界情勢の影響により、海外からお取り寄せとなる洋書・洋古書の入荷が、表示している標準的な納期よりも遅延する場合がございます。
    おそれいりますが、あらかじめご了承くださいますようお願い申し上げます。
  • ◆画像の表紙や帯等は実物とは異なる場合があります。
  • ◆ウェブストアでの洋書販売価格は、弊社店舗等での販売価格とは異なります。
    また、洋書販売価格は、ご注文確定時点での日本円価格となります。
    ご注文確定後に、同じ洋書の販売価格が変動しても、それは反映されません。
  • 製本 Paperback:紙装版/ペーパーバック版/ページ数 439 p.
  • 言語 ENG
  • 商品コード 9783030289539
  • DDC分類 006

Full Description

The development of "intelligent" systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to "intelligent" machines. For sensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner.

The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.

Contents

Towards Explainable Artificial Intelligence.- Transparency: Motivations and Challenges.- Interpretability in Intelligent Systems: A New Concept?.- Understanding Neural Networks via Feature Visualization: A Survey.- Interpretable Text-to-Image Synthesis with Hierarchical Semantic Layout Generation.- Unsupervised Discrete Representation Learning.-  Towards Reverse-Engineering Black-Box Neural Networks.- Explanations for Attributing Deep Neural Network Predictions.- Gradient-Based Attribution Methods.- Layer-Wise Relevance Propagation: An Overview.- Explaining and Interpreting LSTMs.- Comparing the Interpretability of Deep Networks via Network Dissection.- Gradient-Based vs. Propagation-Based Explanations: An Axiomatic Comparison.- The (Un)reliability of Saliency Methods.- Visual Scene Understanding for Autonomous Driving Using Semantic Segmentation.- Understanding Patch-Based Learningof Video Data by Explaining Predictions.- Quantum-Chemical Insights from Interpretable Atomistic Neural Networks.- Interpretable Deep Learning in Drug Discovery.- Neural Hydrology: Interpreting LSTMs in Hydrology.- Feature Fallacy: Complications with Interpreting Linear Decoding Weights in fMRI.- Current Advances in Neural Decoding.- Software and Application Patterns for Explanation Methods.

最近チェックした商品