Modeling word perception using the Elman network

Liou, Cheng-Yuan; Huang, Jau-Chi; Yang, Wen-Chie

doi:10.1016/j.neucom.2008.04.030

Cited by 120 publications

(58 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An auto-encoder is an artificial neural network used for learning efficient codings [4], which aims to learn a compressed representation (encoding) from a data set. It is a powerful tool for dimension reduction, and a basic tool in deep learning.…”

Section: Auto-encodermentioning

confidence: 99%

Parallel auto-encoder for efficient outlier detection

Zhang

Cao

et al. 2013

2013 IEEE International Conference on Big Data

View full text Add to dashboard Cite

Detecting outliers from big data plays an important role in network security. Previous outlier detection algorithms are generally incapable of handling big data. In this paper we present an parallel outlier detection method for big data, based on a new parallel auto-encoder method. Specifically, we build a replicator model of the input data to obtain the representation of sample data. Then, the replicator model is used to measure the replicability of test data, where records having higher reconstruction errors are classified as outliers. Experimental results show the performance of the proposed parallel algorithm.

show abstract

Section: Auto-encodermentioning

confidence: 99%

Parallel auto-encoder for efficient outlier detection

Zhang

Cao

et al. 2013

2013 IEEE International Conference on Big Data

View full text Add to dashboard Cite

show abstract

“…where f (1) (·), f (2) (·) and f (3) (·) are activation functions of the first hidden layer, the second hidden layer, and the output layer, respectively (all the activation functions are sigmoid type). w…”

Section: Context Layermentioning

confidence: 99%

“…For example, w (3) jh (k) is the weight of the connection between the jth neuron in the output layer and the hth output vector in the second hidden layer. v (2) j (k) and v (3) j (k) are the activity level of the second hidden layer and the output layer, respectively. β j (k) and α j (k) are the reversal parameter and the quantum phase of jth qubit neuron in the first hidden layer, respectively.…”

Section: Context Layermentioning

confidence: 99%

“…2: it has a n dimensional input vector x (k) = [x 1 (k) , x 2 (k) , · · · , x n (k)] T and n 3 dimensional output vector y (k) = [y 1 (k) , y 2 (k) , · · · , y n3 (k)] T .The architecture has an output-layer weight vector w (3) n 3 n2 (k) ∈ R n3×1 , a hidden-layer weight vector w (2) n2n1 (k) ∈ R n2×1 , and a context-layer weight vector w (c) n2n2 (k) ∈ R n2×1 . Here n 1 , n 2 and n 3 are the number of neurons in the quantum map layer, the second hidden layer and the output layer, respectively.…”

Section: Qebp Training Algorithmmentioning

confidence: 99%

“…With appropriate structure, ENs are suitable for a wide range of applications including dynamic process modeling [2], process control [3], speech recognition [4],time series prediction [5], [6], dynamic optimization [7]. This has attracted considerable interest from researchers, and makes them improve the performance of Ens, such as robust adaptive gradient-descent training algorithm [8], [9], and so on.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Quantized neuronal modeling: Quantum gate structure in Elman networks

Chai

Xiong

2011

The Fourth International Workshop on Advanced Computational Intelligence

View full text Add to dashboard Cite

This paper investigates the model of Elman network with quantum gate architecture and it's online learning algorithm. The new neural structure, compared with the conventional Elman network (CEN), contains a quantum map layer which can be used for solving the pattern mismatch between the context layer and the input layer. A corresponding training algorithm for this new neural architecture is also presented, as opposed to the standard back-propagation (BP) learning algorithm for ENs. According to the new learning laws, the rotation parameter and the reversal parameter of the quantum gate are updated based on gradient-descent methods. The numerical experiment shows that the proposed network has better generalization performance and faster convergence speed than conventional Elman networks.

show abstract

Deep Learning for Natural Language Processing

2022

Deep Learning

View full text Add to dashboard Cite

Deep learning has emerged as a new area of machine learning research. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. It has been successfully applied to several fields such as images, sounds, text and motion. The techniques developed from deep learning research have already been impacting the research of natural language process. This paper reviews the recent research on deep learning, its applications and recent development in natural language processing.

show abstract

Modeling word perception using the Elman network

Cited by 120 publications

References 16 publications

Parallel auto-encoder for efficient outlier detection

Parallel auto-encoder for efficient outlier detection

Quantized neuronal modeling: Quantum gate structure in Elman networks

Deep Learning for Natural Language Processing

Contact Info

Product

Resources

About