An Introspective Machine

نویسنده

  • G. A. W. Vreeswijk
چکیده

This report was written in order to complete the requirements for my Master's degree, under supervision of prof. In this report, an introspective machine, capable to pass judgement on its own deductive performances, is modelled and analyzed. First, the class of ideal machines which is provided with unlimited resources is studied. Since ideal introspective machines are usually unfeasible, their (so-called) real counterparts are examined in a second stage. Acknowledgements. I am indebted to John-Jules Meyer, not only for his profound criticisms on preliminary versions of the manuscript, but also for making numerous useful suggestions which I have followed. In this connection I also want to express my gratitude to Rens Swart and Eric Verheul for giving comment on one of the last versions of the text.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Confidence Boosting: Improving the Introspectiveness of a Boosted Classifier for E cient Learning

This paper concerns the recently introduced notion of introspective classification. We introduce a variant of the point-biserial correlation coe cient (PBCC) as a measure to characterise the introspective capacity of a classifier and apply it to investigate further the introspective capacity of boosting – a well established, e cient machine learning framework commonly used in robotics. While re...

متن کامل

HIRM: An Algorithm for Developing Introspective Models of Robots

We expand on previous work with the Hybrid Introspective Robot Modeling (HIRM) algorithm, which is an algorithm that develops introspective models of robots with real-world experience. These introspective models that are developed by this algorithm can then be used to accurately plan behaviors in simulation. HIRM is important because using current machine learning techniques to autonomously dev...

متن کامل

Introspective Active Learning for Scalable Semantic Mapping

This paper proposes an active learning framework for semantic mapping in mobile robotics. In particular, our work explores the benefits of an introspective classifier over that of a more traditional non-introspective approach for active data selection. We extend the notion of introspection to a particular sparse Gaussian Process classifier, the Informative Vector Machine (IVM), and show that th...

متن کامل

Driven Learning for Driving: How Introspection Improves Semantic Mapping

This paper explores the suitability of commonly employed classification methods to action-selection tasks in robotics, and argues that a classifier’s introspective capacity is a vital but as yet largely under-appreciated attribute. As illustration we propose an active learning framework for semantic mapping in mobile robotics and demonstrate it in the context of autonomous driving. In this fram...

متن کامل

Representing Self-knowledge for Introspection about Memory Search

This position paper sketches a framework for modeling introspective reasoning and discusses the relevance of that flamework for modeling introspective reasoning about memory search. It argues that effective and flexible memory processing in rich memories should be built on five types of explicitly represented self-knowledge: knowledge about information needs, relationships between different typ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1989