Results 161 to 170 of about 11,885,428 (200)
Some of the next articles are maybe not open access.
Long short-term memory with activation on gradient
Neural Networks, 2023As the number of long short-term memory (LSTM) layers increases, vanishing/exploding gradient problems exacerbate and have a negative impact on the performance of the LSTM. In addition, the ill-conditioned problem occurs in the training process of LSTM and adversely affects its convergence.
Chuan Qin +4 more
openaire +2 more sources
Neural Computation, 1997
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating
Hochreiter, Sepp, Schmidhuber, Jürgen
openaire +3 more sources
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating
Hochreiter, Sepp, Schmidhuber, Jürgen
openaire +3 more sources
A review on the long short-term memory model
Artificial Intelligence Review, 2020Long short-term memory (LSTM) has transformed both machine learning and neurocomputing fields. According to several online sources, this model has improved Google’s speech recognition, greatly improved machine translations on Google Translate, and the answers of Amazon’s Alexa.
Greg Van Houdt +2 more
openaire +1 more source
Immediate Memory for Faces: Long- or Short-Term Memory?
Quarterly Journal of Experimental Psychology, 1973Immediate recognition memory span and short-term forgetting for non-verbal stimuli (“unfamiliar faces”) were investigated in normal subjects and amnesic patients. Surnames were used as a verbal control. It was found that normal subjects had a reliable immediate recognition span of one for faces and that there was no decrement in performance in the ...
E K, Warrington, A M, Taylor
openaire +2 more sources
Hardware aspects of Long Short Term Memory
2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2018This paper focuses on hardware implementation aspects of a Long-Short Term Memory (LSTM) network application. Initially, certain piecewise approximations to activation functions $\sigma$ and tanh are proposed. Next a training procedure is introduced which exploits proposed piecewise approximations.
Ioannis Kouretas, Vassilis Paliouras
openaire +2 more sources
2019
In this chapter, you will learn about recurrent neural networks and long short-term memory models. You will also learn how LSTMs work and how they can be used to detect anomalies and how you can implement anomaly detection using LSTM. You will work through several datasets depicting time series of different types of data such as CPU utilization, taxi ...
Suman Kalyan Adari, Sridhar Alla
openaire +1 more source
In this chapter, you will learn about recurrent neural networks and long short-term memory models. You will also learn how LSTMs work and how they can be used to detect anomalies and how you can implement anomaly detection using LSTM. You will work through several datasets depicting time series of different types of data such as CPU utilization, taxi ...
Suman Kalyan Adari, Sridhar Alla
openaire +1 more source
2012
As discussed in the previous chapter, an important benefit of recurrent neural networks is their ability to use contextual information when mapping between input and output sequences. Unfortunately, for standard RNN architectures, the range of context that can be in practice accessed is quite limited.
openaire +1 more source
As discussed in the previous chapter, an important benefit of recurrent neural networks is their ability to use contextual information when mapping between input and output sequences. Unfortunately, for standard RNN architectures, the range of context that can be in practice accessed is quite limited.
openaire +1 more source
Short-Term Forecasting of Stock Prices Using Long Short Term Memory
2018 International Conference on Information Technology (ICIT), 2018Predicting stock market is not an easy task as it is a chaotic system i.e. whose dynamics are sensitive to arbitrarily small differences in initial conditions. Any small changes in the system can produce compound errors in predicting the future behavior of the system.
Saurav Kumar, Dhruba Ningombam
openaire +1 more source
Short-term load forecasting using a long short-term memory network
2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2017Load forecasting is an essential part of a power system. It enhances the energy-efficiency and reliable operation of the power system. As depicted in the proposal of the smart grid, an increasing number of smart meters have been being installed in many utilities on a global scale.
Chang Liu +3 more
openaire +2 more sources
Long short term memory networks for short-term electric load forecasting
2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017Short-term electricity demand forecasting is critical to utility companies. It plays a key role in the operation of power industry. It becomes all the more important and critical with increasing penetration of renewable energy sources. Short-term load forecasting enables power companies to make informed business decisions in real-time.
Apurva Narayan, Keith W. Hipel
openaire +1 more source