Results 1 - 10 of 173

Dynamic Bayesian Networks: Representation, Inference and Learning

by Kevin Patrick Murphy , 2002
"... Modelling sequential data is important in many areas of science and engineering. Hidden Markov models (HMMs) and Kalman filter models (KFMs) are popular for this because they are simple and flexible. For example, HMMs have been used for speech recognition and bio-sequence analysis, and KFMs have bee ..."
Abstract - Cited by 770 (3 self) - Add to MetaCart
random variable. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. In this thesis, I will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in DBNs, and how to learn DBN models from

Greedy layer-wise training of deep networks

by Yoshua Bengio, Pascal Lamblin, Dan Popovici, Hugo Larochelle , 2006
"... Complexity theory of circuits strongly suggests that deep architectures can be much more efficient (sometimes exponentially) than shallow architectures, in terms of computational elements required to represent some functions. Deep multi-layer neural networks have many levels of non-linearities allow ..."
Abstract - Cited by 394 (48 self) - Add to MetaCart
introduced a greedy layer-wise unsupervised learning algorithm for Deep Belief Networks (DBN), a generative model with many layers of hidden causal variables. In the context of the above optimization problem, we study this al-gorithm empirically and explore variants to better understand its success

Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks

by Arnaud Doucet , Nando de Freitas , Kevin Murphy , Stuart Russell
"... Particle filters (PFs) are powerful sampling-based inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of probability distribution, nonlinearity and non-stationarity. They have appeared in several fields under such names as “conde ..."
Abstract - Cited by 348 (11 self) - Add to MetaCart
Particle filters (PFs) are powerful sampling-based inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of probability distribution, nonlinearity and non-stationarity. They have appeared in several fields under such names

An asynchronous DBN for audio-visual speech recognition

by Kate Saenko, Karen Livescu - In Proc. IEEE Workshop on Spoken Language Technology (SLT), Palm Beach , 2006
"... We investigate an asynchronous two-stream dynamic Bayesian network-based model for audio-visual speech recognition. The model allows the audio and visual streams to de-synchronize within the boundaries of each word. The probability of desynchronization by a given number of states is learned during t ..."
Abstract - Cited by 8 (2 self) - Add to MetaCart
We investigate an asynchronous two-stream dynamic Bayesian network-based model for audio-visual speech recognition. The model allows the audio and visual streams to de-synchronize within the boundaries of each word. The probability of desynchronization by a given number of states is learned during

Multimodal DBN for Predicting High-Quality Answers in cQA portals

by Haifeng Hu, Bingquan Liu, Baoxun Wang, Ming Liu, Xiaolong Wang
"... In this paper, we address the problem for predicting cQA answer quality as a classification task. We propose a multimodal deep belief nets based approach that operates in two stages: First, the joint representation is learned by taking both textual and non-textual features into a deep learning netwo ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
In this paper, we address the problem for predicting cQA answer quality as a classification task. We propose a multimodal deep belief nets based approach that operates in two stages: First, the joint representation is learned by taking both textual and non-textual features into a deep learning

A Hybrid ANN/DBN Approach to Articulatory Feature Recognition

by unknown authors
"... Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (AF) recognition. Previous studies have taken a cascaded approach where separate ANNs are trained for each feature group, making the assumption that features are statistically independent. We address t ..."
Abstract - Add to MetaCart
this by using ANNs to provide virtual evidence to a dynamic Bayesian network (DBN). This gives a hybrid ANN/DBN model and allows modelling of inter-feature dependencies. We demonstrate significant increases in AF recognition accuracy from modelling dependencies between features, and present the results

Efficient Reinforcement Learning in Factored MDPs

by Michael Kearns, Daphne Koller , 1999
"... We present a provably efficient and near-optimal algorithm for reinforcement learning in Markov decision processes (MDPs) whose transition model can be factored as a dynamic Bayesian network (DBN). Our algorithm generalizes the recent algorithm of Kearns and Singh, and assumes that we are given both ..."
Abstract - Cited by 87 (3 self) - Add to MetaCart
We present a provably efficient and near-optimal algorithm for reinforcement learning in Markov decision processes (MDPs) whose transition model can be factored as a dynamic Bayesian network (DBN). Our algorithm generalizes the recent algorithm of Kearns and Singh, and assumes that we are given

Dimensional Emotion Driven Facial Expression Synthesis Based on the Multi-Stream DBN Model

by Hao Wu, Dongmei Jiang, Yong Zhao, Hichem Sahli
"... Abstract—This paper proposes a dynamic Bayesian network (DBN) based MPEG-4 compliant 3D facial animation synthesis method driven by the (Evaluation, Activation) values in the continuous emotion space. For each emotion, a state synchronous DBN model (SS_DBN) is firstly trained using the Cohn-Kanade ( ..."
Abstract - Add to MetaCart
estimation (MLE) criterion, and then used to construct the MPEG-4 compliant 3D facial animation. Compared with the state-of-the-art approaches where the mapping between the emotional space and the FAPs has been made empirically, in our approach the mapping is learned and optimized using DBN to fit the input

A dynamic Bayesian network approach to figure tracking using learned dynamic models

by Vladimir Pavlović, James M. Rehg, Tat-jen Cham, Kevin P. Murphy , 1999
"... The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However, most work on tracking and synthesizing figure motion has employed either simple, generic dynamic models or highly specific hand-tailored ones. Recently, a broad class of learning and inferen ..."
Abstract - Cited by 125 (6 self) - Add to MetaCart
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However, most work on tracking and synthesizing figure motion has employed either simple, generic dynamic models or highly specific hand-tailored ones. Recently, a broad class of learning

Dynamic Bayesian Network (DBN) with Structure Expectation Maximization (SEM) for Modeling of Gene Network from Time Series Gene Expression Data

by Yu Zhang, Zhidong Deng, Hongshan Jiang, Peifa Jia
"... Exploring gene regulatory network is a key topic in molecular biology. In this paper, we present a new dynamic Bayesian network (DBN) framework embedded with structural expectation maximization (SEM) to model gene relationship. It is well-suited for analyzing the time-series data and can deal with c ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Exploring gene regulatory network is a key topic in molecular biology. In this paper, we present a new dynamic Bayesian network (DBN) framework embedded with structural expectation maximization (SEM) to model gene relationship. It is well-suited for analyzing the time-series data and can deal
Results 1 - 10 of 173