Results 31 to 40 of about 92,175 (266)
Recurrent neural network wave functions
Physical Review Research, 2020 A core technology that has emerged from the artificial intelligence revolution is the recurrent neural network (RNN). Its unique sequence-based architecture provides a tractable likelihood estimate with stable training paradigms, a combination that has ...
Mohamed Hibat-Allah +4 more
doaj +1 more source
Bidirectional recurrent neural networks [PDF]
IEEE Transactions on Signal Processing, 1997 In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future frame. This is accomplished by training it simultaneously in positive and negative time direction.
Mike Schuster, Kuldip K. Paliwal
openaire +1 more source
On the quantization of recurrent neural networks
CoRR, 2021 Integer quantization of neural networks can be defined as the approximation of the high precision computation of the canonical neural network formulation, using reduced integer precision. It plays a significant role in the efficient deployment and execution of machine learning (ML) systems, reducing memory consumption and leveraging typically faster ...
Jian Li, Raziel Alvarez
openaire +2 more sources
Recurrent Neural Network Regularization
CoRR, 2014 We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on
Wojciech Zaremba +2 more
openaire +2 more sources
Interpretation of recurrent neural networks [PDF]
Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop, 2002 This paper addresses techniques for interpretation and characterization of trained recurrent nets for time series problems. In particular, we focus on assessment of effective memory and suggest an operational definition of memory. Further we discuss the evaluation of learning curves.
Pedersen, Morten With +1 more
openaire +1 more source
General Recurrent Neural Network for Solving Generalized Linear Matrix Equation
Complexity, 2017 This brief proposes a general framework of the nonlinear recurrent neural network for solving online the generalized linear matrix equation (GLME) with global convergence property. If the linear activation function is utilized, the neural state matrix of
Zhan Li, Hong Cheng, Hongliang Guo
doaj +1 more source
Clustering Based on Continuous Hopfield Network
Mathematics, 2022 Clustering aims to group n data samples into k clusters. In this paper, we reformulate the clustering problem into an integer optimization problem and propose a recurrent neural network with n×k neurons to solve it. We prove the stability and convergence
Yao Xiao +3 more
doaj +1 more source
Sensors, 2021 In this study, a scheme of remaining useful lifetime (RUL) prognosis from raw acoustic emission (AE) data is presented to predict the concrete structure’s failure before its occurrence, thus possibly prolong its service life and minimizing the risk of ...
Tuan-Khai Nguyen +2 more
doaj +1 more source
Neural Approximators for Variable-Order Fractional Calculus Operators (VO-FC)
IEEE Access, 2022 The paper presents research on the approximation of variable-order fractional operators by recurrent neural networks. The research focuses on two basic variable-order fractional operators, i.e., integrator and differentiator.
Bartosz Puchalski
doaj +1 more source
Detection of Shoplifting on Video Using a Hybrid Network
Computation, 2022 Shoplifting is a major problem for shop owners and many other parties, including the police. Video surveillance generates huge amounts of information that staff cannot process in real time.
Lyudmyla Kirichenko +3 more
doaj +1 more source