Deep recurrent neural networks based binaural speech segregation for the selection of closest target of interest

2017 ◽  
Vol 77 (15) ◽  
pp. 20129-20156 ◽  
Author(s):  
R. Venkatesan ◽  
A. Balaji Ganesh
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Speech Segregation ◽  
Selection Of

scholarly journals A New Hyper-Parameter Optimization Method for Power Load Forecast Based on Recurrent Neural Networks

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 163
Author(s):  
Yaru Li ◽  
Yulai Zhang ◽  
Yongping Cai
Keyword(s):  
Neural Networks ◽  
Parameter Optimization ◽  
Recurrent Neural Networks ◽  
Critical Role ◽  
Optimization Method ◽  
Bayesian Optimization ◽  
Power Load ◽  
Gradient Calculation ◽  
Truncated Newton ◽  
Selection Of

The selection of the hyper-parameters plays a critical role in the task of prediction based on the recurrent neural networks (RNN). Traditionally, the hyper-parameters of the machine learning models are selected by simulations as well as human experiences. In recent years, multiple algorithms based on Bayesian optimization (BO) are developed to determine the optimal values of the hyper-parameters. In most of these methods, gradients are required to be calculated. In this work, the particle swarm optimization (PSO) is used under the BO framework to develop a new method for hyper-parameter optimization. The proposed algorithm (BO-PSO) is free of gradient calculation and the particles can be optimized in parallel naturally. So the computational complexity can be effectively reduced which means better hyper-parameters can be obtained under the same amount of calculation. Experiments are done on real world power load data,where the proposed method outperforms the existing state-of-the-art algorithms,BO with limit-BFGS-bound (BO-L-BFGS-B) and BO with truncated-newton (BO-TNC),in terms of the prediction accuracy. The errors of the prediction result in different models show that BO-PSO is an effective hyper-parameter optimization method.

scholarly journals Approximation of phenol concentration using novel hybrid computational intelligence methods

2014 ◽  
Vol 24 (1) ◽  
pp. 165-181 ◽  
Author(s):  
Pawel Plawiak ◽  
Ryszard Tadeusiewicz
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Computational Intelligence ◽  
Recurrent Neural Networks ◽  
Phenol Concentration ◽  
Neural Systems ◽  
Feed Forward ◽  
Computational Intelligence Methods ◽  
Lm Algorithm ◽  
Selection Of

Abstract This paper presents two innovative evolutionary-neural systems based on feed-forward and recurrent neural networks used for quantitative analysis. These systems have been applied for approximation of phenol concentration. Their performance was compared against the conventional methods of artificial intelligence (artificial neural networks, fuzzy logic and genetic algorithms). The proposed systems are a combination of data preprocessing methods, genetic algorithms and the Levenberg-Marquardt (LM) algorithm used for learning feed forward and recurrent neural networks. The initial weights and biases of neural networks chosen by the use of a genetic algorithm are then tuned with an LM algorithm. The evaluation is made on the basis of accuracy and complexity criteria. The main advantage of proposed systems is the elimination of random selection of the network weights and biases, resulting in increased efficiency of the systems.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Sign in / Sign up

Export Citation Format

Share Document