Probabilistic machine learning and artificial intelligence

By Zoubin Ghahramani. 2015

2,051 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Management Science and Operations Research, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Management Science and Operations Research

In Probabilistic & Bayesian Methods

Citations in the corpus

PAC-Bayesian Theory Meets Bayesian Inference (2016, neutral): “1 In this work, we provide a direct connection between Bayesian inference techniques [summarized by 6, 15] and PAC-Bayesian risk bounds in a general setup.”
Pyro: Deep Universal Probabilistic Programming (2018, background): “In recent years, richly structured probabilistic models have demonstrated promising results on a number of fundamental problems in AI (Ghahramani (2015)).”
An Introduction to Probabilistic Programming (2018, background): “A large number of computational neuroscientists, cognitive scientists, machine learning researchers believe in a well-established formal model of how agents choose and plan their actions (Levine, 2018; Tenenbaum et al., 2011; Ghahramani, 2015).”
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (2015, background): “For the 12 images, the model predicts classes [1 1 1 1 1 5 5 7 7 7 7 7].”
Interaction Networks for Learning about Objects, Relations and Physics (2016, background): “Structured models [7] can exploit rich, explicit knowledge of relations among objects, independent of the objects themselves, which supports general-purpose reasoning across diverse contexts.”
Relational inductive biases, deep learning, and graph networks (2018, neutral): “…approaches, including logic, grammars, classic planning, graphical models, causal reasoning, Bayesian nonparametrics, and probabilistic programming (Chomsky, 1957; Nilsson and Fikes, 1970; Pearl, 1986, 2009; Russell and Norvig, 2009; Hjort et al., 2010; Goodman et al., 2012; Ghahramani, 2015).”
Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations (2017, background): “Data-driven methods are taking center stage across many disciplines of science, and machine learning techniques have achieved groundbreaking results across a diverse spectrum of pattern recognition tasks [10, 15, 16].”
A Review of Vibration-Based Damage Detection in Civil Structures: From Traditional Methods to Machine Learning and Deep Learning Applications (2020, background): “Therefore, a major challenge faced by modern AI systems was to find alternative ways of teaching intuitive and common-sense knowledge to computers [76].”
Laplace Redux - Effortless Bayesian Deep Learning (2021, background): “Bayesian modeling [4, 5] provides a principled and unified approach to tackle these issues by (i) equipping models with robust uncertainty estimates [6], (ii) enabling models to learn continually by capturing past information [7], and (iii) allowing for automated model selection by optimally trading”