Bayesian models of conceptual development: Learning as building models of the world
TD Ullman, JB Tenenbaum - Annual Review of Developmental …, 2020 - annualreviews.org
A Bayesian framework helps address, in computational terms, what knowledge children start
with and how they construct and adapt models of the world during childhood. Within this …
with and how they construct and adapt models of the world during childhood. Within this …
From word models to world models: Translating from natural language to the probabilistic language of thought
How does language inform our downstream thinking? In particular, how do humans make
meaning from language--and how can we leverage a theory of linguistic meaning to build …
meaning from language--and how can we leverage a theory of linguistic meaning to build …
Gen: a general-purpose probabilistic programming system with programmable inference
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 …
models, existing systems lack the flexibility and efficiency needed for practical use with more …
Phenomenal yet puzzling: Testing inductive reasoning capabilities of language models with hypothesis refinement
The ability to derive underlying principles from a handful of observations and then
generalize to novel situations--known as inductive reasoning--is central to human …
generalize to novel situations--known as inductive reasoning--is central to human …
Online bayesian goal inference for boundedly rational planning agents
T Zhi-Xuan, J Mann, T Silver… - Advances in neural …, 2020 - proceedings.neurips.cc
People routinely infer the goals of others by observing their actions over time. Remarkably,
we can do so even when those actions lead to failure, enabling us to assist others when we …
we can do so even when those actions lead to failure, enabling us to assist others when we …
Human-like few-shot learning via bayesian reasoning over natural language
K Ellis - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
A core tension in models of concept learning is that the model must carefully balance the
tractability of inference against the expressivity of the hypothesis class. Humans, however …
tractability of inference against the expressivity of the hypothesis class. Humans, however …
SPPL: probabilistic programming with fast exact symbolic inference
We present the Sum-Product Probabilistic Language (SPPL), a new probabilistic
programming language that automatically delivers exact solutions to a broad range of …
programming language that automatically delivers exact solutions to a broad range of …
Sequential Monte Carlo learning for time series structure discovery
This paper presents a new approach to automatically discovering accurate models of
complex time series data. Working within a Bayesian nonparametric prior over a symbolic …
complex time series data. Working within a Bayesian nonparametric prior over a symbolic …
Astra: understanding the practical impact of robustness for probabilistic programs
We present the first systematic study of effectiveness of robustness transformations on a
diverse set of 24 probabilistic programs representing generalized linear models, mixture …
diverse set of 24 probabilistic programs representing generalized linear models, mixture …
Trace types and denotational semantics for sound programmable inference in probabilistic languages
Modern probabilistic programming languages aim to formalize and automate key aspects of
probabilistic modeling and inference. Many languages provide constructs for programmable …
probabilistic modeling and inference. Many languages provide constructs for programmable …