Comparing the Modeling Powers of RNN and HMM

Salaün, Achille; Petetin, Yohan; Desbouvries, François

doi:10.1109/icmla.2019.00246

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From a theoretical point of view, we believe that the derivations that led to the neural interpretation of Gaussian mixture models could benefit other mixture models such as the von Mises-Fisher mixture models (Hasnat et al, 2017) or hidden Markov models (HMM). The case of Gaussian-HMM seems especially promising as it allows to bridge with Recurrent networks (Salaün et al, 2019). followed by a dense layer with a dimension 3 output.…”

Section: Discussionmentioning

confidence: 99%

Joint optimization of an autoencoder for clustering and embedding

et al. 2021

View full text Add to dashboard Cite

Deep embedded clustering has become a dominating approach to unsupervised categorization of objects with deep neural networks. The optimization of the most popular methods alternates between the training of a deep autoencoder and a k-means clustering of the autoencoder’s embedding. The diachronic setting, however, prevents the former to benefit from valuable information acquired by the latter. In this paper, we present an alternative where the autoencoder and the clustering are learned simultaneously. This is achieved by providing novel theoretical insight, where we show that the objective function of a certain class of Gaussian mixture models (GMM’s) can naturally be rephrased as the loss function of a one-hidden layer autoencoder thus inheriting the built-in clustering capabilities of the GMM. That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding. Experiments confirm the equivalence between the clustering module and Gaussian mixture models. Further evaluations affirm the empirical relevance of our deep architecture as it outperforms related baselines on several data sets.

show abstract

Section: Discussionmentioning

confidence: 99%

Joint optimization of an autoencoder for clustering and embedding

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Subsequently, the visual representations of an FFNN and RNN have no meaning other than displaying the architecture of the network. Even though DBNs, HMMs, and RNNs can be used for estimating an unobserved variable given a sequence of observations, RNNs deduce this latent variable deterministically based on the observed sequence instead of making use of, for example, a Markov chain [40].…”

Section: B Driver Intention Recognition Methodsmentioning

confidence: 99%

Driver Intention Recognition: State-of-the-Art Review

Vellenga

Steinhauer

Karlsson

et al. 2022

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Every year worldwide more than one million people die and a further 50 million people are injured in traffic accidents. Therefore, the development of car safety features that actively support the driver in preventing accidents, is of utmost importance to reduce the number of injuries and fatalities. However, to establish this support it is necessary that the advanced driver assistance system (ADAS) understands the driver's intended behavior in advance. The growing variety of sensors available for vehicles together with improved computer vision techniques, hence led to increased research directed towards inferring the driver's intentions. This article reviews 64 driver intention recognition studies with regard to the maneuvers considered, the driving features included, the AI methods utilized, the achieved performance within the presented experiments, and the open challenges identified by the respected researchers. The article provides a high level analysis of the current technology readiness level of driver intention recognition technology to address the challenges to enable reliable driver intention recognition, such as the system architecture, implementation, and the purpose of the technology.

show abstract

“…HMMs and RNNs share out similarities since they comprise latent variables. However, they differ in the way of building these variables [31]. The choice of either HMMs or RNNs depends on the application domain.…”

Section: ) Classificationmentioning

confidence: 99%

Deep Sparse Auto-Encoder Features Learning for Arabic Text Recognition

et al. 2021

View full text Add to dashboard Cite

One of the most recent challenging issues of pattern recognition and artificial intelligence is Arabic text recognition. This research topic is still a pervasive and unaddressed research field, because of several factors. Complications arise due to the cursive nature of the Arabic writing, character similarities, unlimited vocabulary, use of multi-size and mixed-fonts, etc. To handle these challenges, an automatic Arabic text recognition requires building a robust system by computing discriminative features and applying a rigorous classifier together to achieve an improved performance. In this work, we introduce a new deep learning based system that recognizes Arabic text contained in images. We propose a novel hybrid network, combining a Bag-of-Feature (BoF) framework for feature extraction based on a deep Sparse Auto-Encoder (SAE), and Hidden Markov Models (HMMs), for sequence recognition. Our proposed system, termed BoF-deep SAE-HMM, is tested on four datasets, namely the printed Arabic line images Printed KHATT (P-KHATT), the benchmark printed word images Arabic Printed Text Image (APTI), the benchmark handwritten Arabic word images IFN/ENIT, and the benchmark handwritten digits images Modified National Institute of Standards and Technology (MNIST).

show abstract

Comparing the Modeling Powers of RNN and HMM

Cited by 11 publications

References 10 publications

Joint optimization of an autoencoder for clustering and embedding

Joint optimization of an autoencoder for clustering and embedding

Driver Intention Recognition: State-of-the-Art Review

Deep Sparse Auto-Encoder Features Learning for Arabic Text Recognition

Contact Info

Product

Resources

About