paper-with-me

Papers

Building fast Bayesian computing machines out of intentionally stochastic, digital parts

2014-02-20 · Vikash Mansinghka, Eric Jonas

The brain interprets ambiguous sensory information faster and more reliably than modern computers, using neurons that are slower and less reliable than logic gates. But Bayesian inference, which underpins many computational models of perception and cognition, appears computationally challenging even given modern transistor speeds and energy budgets. The computational principles and structures needed to narrow this gap are unknown. Here we show how to build fast Bayesian computing machines using intentionally stochastic, digital parts, narrowing this efficiency gap by multiple orders of magnitude. We find that by connecting stochastic digital components according to simple mathematical rules, one can build massively parallel, low precision circuits that solve Bayesian inference problems and are compatible with the Poisson firing statistics of cortical neurons. We evaluate circuits for depth and motion perception, perceptual learning and causal reasoning, each performing inference over 10,000+ latent variables in real time - a 1,000x speed advantage over commodity microprocessors. These results suggest a new role for randomness in the engineering and reverse-engineering of intelligent computation.

📄 PDF Abstract BibTeX arXiv:1402.4914

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Showing versus doing: Teaching by demonstration

2016-12-01 · NeurIPS 2016 12 · Mark K. Ho, Michael Littman, James Macglashan, Fiery Cushman 외

People often learn from others' demonstrations, and classic inverse reinforcement learning (IRL) algorithms have brought us closer to realizing this capacity in machines. In contrast, teaching by demonstration has been l…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Higher-order Derivatives of Weighted Finite-state Machines

2021-06-01 · ACL 2021 5 · Ran Zmigrod, Tim Vieira, Ryan Cotterell

Weighted finite-state machines are a fundamental building block of NLP systems. They have withstood the test of time -- from their early use in noisy channel models in the 1990s up to modern-day neurally parameterized co…

Bayesian Nonlinear Support Vector Machines for Big Data

2017-07-18 · Florian Wenzel, Theo Galy-Fajou, Matthaeus Deutsch, Marius Kloft

We propose a fast inference method for Bayesian nonlinear support vector machines that leverages stochastic variational inference and inducing points. Our experiments show that the proposed method is faster than competin…

Variational Inference

Generating Bayesian Network Models from Data Using Tsetlin Machines

2023-05-17 · Christian D. Blakely

Bayesian networks (BN) are directed acyclic graphical (DAG) models that have been adopted into many fields for their strengths in transparency, interpretability, probabilistic reasoning, and causal modeling. Given a set …

Compositional optimization of quantum circuits for quantum kernels of support vector machines

2022-03-25 · Elham Torabian, Roman V. Krems

While quantum machine learning (ML) has been proposed to be one of the most promising applications of quantum computing, how to build quantum ML models that outperform classical ML remains a major open question. Here, we…

Bayesian OptimizationBIG-bench Machine LearningClassificationOpen-Ended Question Answering+1