Learning Naïve Physics Models by Analogical Generalization

نویسندگان

  • Scott E. Friedman
  • Jason Taylor
  • Kenneth D. Forbus
چکیده

How do people learn intuitive models of the world from experience? We describe a simulation that uses analogical generalization to learn naïve models of pushing and blocking from experience. Experiences are represented by a type of comic strip, consisting of sequences of sketches and simplified English that are automatically encoded by the simulation. We show that the models it learns are compatible with naïve models found in the literature, and analyze the effects of presentation order.

برای دانلود رایگان 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

Learning Naïve Physics Models and Misconceptions

Modeling how intuitive physics concepts are learned from experience is an important challenge for cognitive science. We describe a simulation that can learn intuitive causal models from a corpus of multimodal stimuli, consisting of sketches and text. The simulation uses analogical generalization and statistical tests over qualitative representations it constructs from the stimuli to learn abstr...

متن کامل

Extending Analogical Generalization with Near-Misses

Concept learning is a central problem for cognitive systems. Generalization techniques can help organize examples by their commonalities, but comparisons with non-examples, near-misses, can provide discrimination. Early work on near-misses required hand-selected examples by a teacher who understood the learner’s internal representations. This paper introduces Analogical Learning by Integrating ...

متن کامل

Action Recognition from Skeleton Data Via Analogical Generalization

Human action recognition remains a difficult problem for AI. Traditional machine learning techniques have had some success, but have two disadvantages. First, these models are typically black boxes whose internal models are not inspectable and whose results are not explainable. Second, typically massive amounts of data are needed to achieve good recognition performance. This paper describes a n...

متن کامل

Action Recognition from Skeleton Data via Analogical Generalization over Qualitative Representations

Human action recognition remains a difficult problem for AI. Traditional machine learning techniques can have high recognition accuracy, but they are typically black boxes whose internal models are not inspectable and whose results are not explainable. This paper describes a new pipeline for recognizing human actions from skeleton data via analogical generalization. Specifically, starting with ...

متن کامل

Learning concepts from sketches via analogical generalization and near-misses

Modeling how concepts are learned from experience is an important challenge for cognitive science. In cognitive psychology, progressive alignment, i.e., comparing highly similar examples, has been shown to lead to rapid learning. In AI, providing negative examples (near-misses) that are very similar has been proposed as another way to accelerate learning. This paper describes a model of concept...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009