Memory as a computational resource

I Dasgupta, SJ Gershman - Trends in cognitive sciences, 2021 - cell.com
Computer scientists have long recognized that naive implementations of algorithms often
result in a paralyzing degree of redundant computation. More sophisticated implementations …

Synthesizing theories of human language with Bayesian program induction

K Ellis, A Albright, A Solar-Lezama… - Nature …, 2022 - nature.com
Automated, data-driven construction and evaluation of scientific models and theories is a
long-standing challenge in artificial intelligence. We present a framework for algorithmically …

A theory of learning to infer.

I Dasgupta, E Schulz, JB Tenenbaum… - Psychological …, 2020 - psycnet.apa.org
Bayesian theories of cognition assume that people can integrate probabilities rationally.
However, several empirical findings contradict this proposition: human probabilistic …

Towards a cross-level understanding of Bayesian inference in the brain

CHS Lin, MI Garrido - Neuroscience & Biobehavioral Reviews, 2022 - Elsevier
Perception emerges from unconscious probabilistic inference, which guides behaviour in
our ubiquitously uncertain environment. Bayesian decision theory is a prominent …

Probability flow solution of the fokker–planck equation

NM Boffi, E Vanden-Eijnden - Machine Learning: Science and …, 2023 - iopscience.iop.org
The method of choice for integrating the time-dependent Fokker–Planck equation (FPE) in
high-dimension is to generate samples from the solution via integration of the associated …

Variational resampling

O Kviman, N Branchini, V Elvira… - International …, 2024 - proceedings.mlr.press
We cast the resampling step in particle filters (PFs) as a variational inference problem,
resulting in a new class of resampling schemes: variational resampling. Variational …

Remembrance of inferences past: Amortization in human hypothesis generation

I Dasgupta, E Schulz, ND Goodman, SJ Gershman - Cognition, 2018 - Elsevier
Bayesian models of cognition assume that people compute probability distributions over
hypotheses. However, the required computations are frequently intractable or prohibitively …

Multiple importance sampling elbo and deep ensembles of variational approximations

O Kviman, H Melin, H Koptagel… - International …, 2022 - proceedings.mlr.press
In variational inference (VI), the marginal log-likelihood is estimated using the standard
evidence lower bound (ELBO), or improved versions as the importance weighted ELBO …

Finding structure in multi-armed bandits

E Schulz, NT Franklin, SJ Gershman - Cognitive psychology, 2020 - Elsevier
How do humans search for rewards? This question is commonly studied using multi-armed
bandit tasks, which require participants to trade off exploration and exploitation. Standard …

Hierarchical structure is employed by humans during visual motion perception

J Bill, H Pailian, SJ Gershman… - Proceedings of the …, 2020 - National Acad Sciences
In the real world, complex dynamic scenes often arise from the composition of simpler parts.
The visual system exploits this structure by hierarchically decomposing dynamic scenes …