Neuro-symbolic artificial intelligence: The state of the art
Neuro-symbolic AI is an emerging subfield of Artificial Intelligence that brings together two
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
The frontier of simulation-based inference
Many domains of science have developed complex simulations to describe phenomena of
interest. While these simulations provide high-fidelity models, they are poorly suited for …
interest. While these simulations provide high-fidelity models, they are poorly suited for …
SBI--A toolkit for simulation-based inference
A Tejero-Cantero, J Boelts, M Deistler… - arXiv preprint arXiv …, 2020 - arxiv.org
Scientists and engineers employ stochastic numerical simulators to model empirically
observed phenomena. In contrast to purely statistical models, simulators express scientific …
observed phenomena. In contrast to purely statistical models, simulators express scientific …
Benchmarking simulation-based inference
JM Lueckmann, J Boelts, D Greenberg… - International …, 2021 - proceedings.mlr.press
Recent advances in probabilistic modelling have led to a large number of simulation-based
inference algorithms which do not require numerical evaluation of likelihoods. However, a …
inference algorithms which do not require numerical evaluation of likelihoods. However, a …
Simulation intelligence: Towards a new generation of scientific methods
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …
computing, where a motif is an algorithmic method that captures a pattern of computation …
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 …
Automatic differentiation in machine learning: a survey
Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine
learning. Automatic differentiation (AD), also called algorithmic differentiation or simply" auto …
learning. Automatic differentiation (AD), also called algorithmic differentiation or simply" auto …
Sequential neural likelihood: Fast likelihood-free inference with autoregressive flows
G Papamakarios, D Sterratt… - The 22nd international …, 2019 - proceedings.mlr.press
Abstract We present Sequential Neural Likelihood (SNL), a new method for Bayesian
inference in simulator models, where the likelihood is intractable but simulating data from …
inference in simulator models, where the likelihood is intractable but simulating data from …
Learning disentangled representations with semi-supervised deep generative models
B Paige, JW Van De Meent… - Advances in neural …, 2017 - proceedings.neurips.cc
Variational autoencoders (VAEs) learn representations of data by jointly training a
probabilistic encoder and decoder network. Typically these models encode all features of …
probabilistic encoder and decoder network. Typically these models encode all features of …
Training deep neural density estimators to identify mechanistic models of neural dynamics
Mechanistic modeling in neuroscience aims to explain observed phenomena in terms of
underlying causes. However, determining which model parameters agree with complex and …
underlying causes. However, determining which model parameters agree with complex and …