An Introduction to Hidden Markov Models and Bayesian Networks

By Zoubin Ghahramani. International journal of pattern recognition and artificial intelligence, 2001

855 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/6ddb5df89a4b03620e1a3c73484567ed5c7c41db

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 Statistics and Probability

Citations in the corpus

Estimating a State-Space Model from Point Process Observations (2003, methodology): “Many extensions of this algorithm to both nongaussian, nonlinear state equations and nongaussian, nonlinear observation processes have been studied (Ljung & Söderström, 1987; Kay, 1988; Kitagawa & Gersh, 1996; Roweis & Ghahramani, 1999; Gharamani, 2001).”
A comparison of static, dynamic, and hybrid analysis for malware detection (2015, background): “For a thorough discussion of the solutions toHMM Problems 1 through 3, see [43]; for additional information see [23] or the classic introduction [34].”
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (2020, background): “For example, the context variable could be the strategy of an opponent in a game [71, 50, 79, 53], regimes in time-series forecasting [58, 20, 9], the mood of a user when navigating a content platform in recommender systems [26, 74] or any unobserved variable in RL, e.”
Physics-informed deep generative models (2018, positive): “In this work, we revisit these approaches from a probabilistic standpoint [17, 18, 19] and develop an adversarial inference framework [20, 21, 22, 23] to enable the posterior characterization [24, 25] of the uncertainty associated with the model predictions.”
Sequence-Aware Recommender Systems (2018, methodology): “Variants of RNNs such as LSTM [36] and GRU [23], by means of their sophisticated hidden dynamics, can model much longer and complex temporal dependencies than other approaches like Hidden Markov Models [34].”
Learning Action Representations for Reinforcement Learning (2019, methodology): “…for actions that captures this structure, we consider a standard Markov property, often used for learning probabilistic graphical models [Ghahramani, 2001], and make the following assumption that the transition information can be sufﬁciently encoded to infer the action that was executed.”
Hidden semi-Markov models (2010, neutral): “Detailed review for the conventional HMM can be found in the tutorial by Rabiner [150], the overview by Ephraim and Merhav [57], the Bayesian networks-based discussion by Ghahramani [66], and the book by Cappe et al. [29].”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, background): “Such structured representations are known under the name of dynamic Bayesian networks [33].”
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models (2002, methodology): “Quite recently, Bayesian techniques have been introduced for the problem of learning the mappings f and g in equations 3.1 and 3.2 in Briegel and Tresp (1999), Ghahramani and Roweis (1999), and Roweis and Ghahramani (2001).”
Towards an automatic early stress recognition system for office environments based on multimodal measurements: A review (2016, methodology): “Algorithms such as Hidden Markov Models or dynamic Bayesian Networks [177] have been used to model typical complex activities.”
MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting (2018, methodology): “We refer the reader to [42], [43], [44] and [45] for a more detailed discussion of Variational Bayes GMMs.”