Designing Perceptual Puzzles by Differentiating Probabilistic Programs
We design new visual illusions by finding "adversarial examples" for principled models of human perception -- specifically, for probabilistic models, which treat vision as Bayesian inference. To perform this search efficiently, we design a differentiable probabilistic programming language, whose API exposes MCMC inference as a first-class differentiable function. We demonstrate our method by automatically creating illusions for three features of human vision: color constancy, size constancy, and face perception.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceColor ConstancyProbabilistic ProgrammingSimilar Papers 제목 키워드 기반
Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language
Solving puzzles in natural language poses a long-standing challenge in AI. While large language models (LLMs) have recently shown impressive capabilities in a variety of tasks, they continue to struggle with complex puzz…
Natural Language UnderstandingRethinking Variational Inference for Probabilistic Programs with Stochastic Support
We introduce Support Decomposition Variational Inference (SDVI), a new variational inference (VI) approach for probabilistic programs with stochastic support. Existing approaches to this problem rely on designing a singl…
Variational InferencePUZZLES: A Benchmark for Neural Algorithmic Reasoning
Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as mo…
Decision MakingLogical ReasoningReinforcement Learning (RL)Solving probability puzzles with logic toolkit
The proposed approach is to formalise the probabilistic puzzle in equational FOL. Two formalisations are needed: one theory for all models of the given puzzle, and a second theory for the favorable models. Then Mace4 - t…
ADAPTIVE GENERATION OF PROGRAMMING PUZZLES
AI today is far from being able to write complex programs. What type of problems would be best for computers to learn to program, and how should such problems be generated? To answer the first question, we suggest progra…
Program Synthesis