People have strong intuitions about the influence objects exert upon one another when they collide. Because people's judgments appear to deviate from Newtonian mechanics, psychologists have suggested that people depend on a variety of task-specific heuristics. This leaves open the question of how these heuristics could be chosen, and how to integrate them into a unified model that can explain human judgments across a wide range of physical reasoning tasks. We propose an alternative framework, in which people's judgments are based on optimal statistical inference over a Newtonian physical model that incorporates sensory noise and intrinsic uncertainty about the physical properties of the objects being viewed. This "noisy Newton" framework can be applied to a multitude of judgments, with people's answers determined by the uncertainty they have for physical variables and the constraints of Newtonian mechanics. We investigate a range of effects in mass judgments that have previously been taken as strong evidence for heuristic use and show that they are well explained by the interplay between Newtonian constraints and sensory uncertainty. We also consider an extended model that handles causality judgments, and obtain good quantitative agreement with human judgments across tasks that involve different judgment types with a single consistent set of parameters. RECONCILING INTUITIVE PHYSICS AND NEWTONIAN MECHANICS 4Reconciling Intuitive Physics and Newtonian Mechanics for Colliding Objects People believe that they understand how everyday physical objects behave. However, our intuitive understanding appears to be inconsistent with Newtonian mechanics: People often predict that an object that is swung around will follow a curved path when released (McCloskey, Caramazza, & Green, 1980) and predict that a ball dropped from a moving object will fall straight downwards (McCloskey, Washburn, & Felch, 1983;Kaiser, Proffitt, Whelan, & Hecht, 1992).Following the ground-breaking work of Michotte (1963), collisions between objects have been used as the basis for one of the most comprehensive investigations of the relationship between intuitive and Newtonian mechanics (A. Cohen, 2006;A. Cohen & Ross, 2009;Runeson, 1983Runeson, , 1995Runeson & Vedeler, 1993;Runeson, Juslin, & Olsson, 2000;Schlottmann & Anderson, 1993;Todd & Warren, 1982). In a typical experiment, participants observe a collision between two objects and are then asked to make a judgment about the physical properties of the objects involved (such as their relative mass) or the relationships between them (such as whether one object caused the other to move). Analysis of these judgments has revealed significant deviations from the predictions of Newtonian mechanics, which have been held up as evidence that intuitive physics is based on a set of shortcuts or heuristics (Andersson & Runeson, 2008;A. Cohen, 2006;A. Cohen & Ross, 2009;Gilden, 1991;Michotte, 1963;Runeson et al., 2000;Schlottmann & Anderson, 1993;Todd & Warren, 1982). In this paper, we show that dissoc...
Recent progress on probabilistic modeling and statistical learning, coupled with the availability of large training datasets, has led to remarkable progress in computer vision. Generative probabilistic models, or "analysis-by-synthesis" approaches, can capture rich scene structure but have been less widely applied than their discriminative counterparts, as they often require considerable problem-specific engineering in modeling and inference, and inference is typically seen as requiring slow, hypothesize-and-test Monte Carlo methods. Here we present Picture, a probabilistic programming language for scene understanding that allows researchers to express complex generative vision models, while automatically solving them using fast general-purpose inference machinery. Picture provides a stochastic scene language that can express generative models for arbitrary 2D/3D scenes, as well as a hierarchy of representation layers for comparing scene hypotheses with observed images by matching not simply pixels, but also more abstract features (e.g., contours, deep neural network activations). Inference can flexibly integrate advanced Monte Carlo strategies with fast bottomup data-driven methods. Thus both representations and inference strategies can build directly on progress in discriminatively trained systems to make generative vision more robust and efficient. We use Picture to write programs for 3D face analysis, 3D human pose estimation, and 3D object reconstruction -each competitive with specially engineered baselines.
Although probabilistic programming is widely used for some restricted classes of statistical models, existing systems lack the flexibility and efficiency needed for practical use with more challenging models arising in fields like computer vision and robotics. This paper introduces Gen, a generalpurpose probabilistic programming system that achieves modeling flexibility and inference efficiency via several novel language constructs: (i) the generative function interface for encapsulating probabilistic models; (ii) interoperable modeling languages that strike different flexibility/efficiency tradeoffs; (iii) combinators that exploit common patterns of conditional independence; and (iv) an inference library that empowers users to implement efficient inference algorithms at a high level of abstraction. We show that Gen outperforms state-of-the-art probabilistic programming systems, sometimes by multiple orders of magnitude, on diverse problems including object tracking, estimating 3D body pose from a depth image, and inferring the structure of a time series. CCS Concepts • Mathematics of computing → Probabilistic reasoning algorithms.
We describe Venture, an interactive virtual machine for probabilistic programming that aims to be sufficiently expressive, extensible, and efficient for general-purpose use. Like Church, probabilistic models and inference problems in Venture are specified via a Turing-complete, higher-order probabilistic language descended from Lisp. Unlike Church, Venture also provides a compositional language for custom inference strategies, assembled from scalable implementations of several exact and approximate techniques. Venture is thus applicable to problems involving widely varying model families, dataset sizes and runtime/accuracy constraints. We also describe four key aspects of Venture's implementation that build on ideas from probabilistic graphical models. First, we describe the stochastic procedure interface (SPI) that specifies and encapsulates primitive random variables, analogously to conditional probability tables in a Bayesian network. The SPI supports custom control flow, higher-order probabilistic procedures, partially exchangeable sequences and "likelihood-free" stochastic simulators, all with custom proposals. It also supports the integration of external models that dynamically create, destroy and perform inference over latent variables hidden from Venture. Second, we describe probabilistic execution traces (PETs), which represent execution histories of Venture programs. Like Bayesian networks, PETs capture conditional dependencies, but PETs also represent existential dependencies and exchangeable coupling. Third, we describe partitions of execution histories called scaffolds that can be efficiently constructed from PETs and that factor global inference problems into coherent sub-problems. Finally, we describe a family of stochastic regeneration algorithms for efficiently modifying PET fragments contained within scaffolds without visiting conditionally independent random choices. Stochastic regeneration insulates inference algorithms from the complexities introduced by changes in execution structure, with runtime that scales linearly in cases where previous approaches often scaled quadratically and were therefore impractical. We show how to use stochastic regeneration and the SPI to implement general-purpose inference strategies such as Metropolis-Hastings, Gibbs sampling, and blocked proposals based on hybrids with both particle Markov chain Monte Carlo and mean-field variational inference techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.