Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

Efficient Online Learning Algorithms Based on LSTM Neural Networks

• Tolga Ergen, Suleyman Serdar Kozat
• IEEE Transactions on Neural Networks and Learning…
• 2018

We investigate online nonlinear regression and introduce novel regression structures based on the long short term memory (LSTM) networks. For the introduced structures, we also provide highly… (More)

Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networks

• Tolga Ergen, Ali Hassan Mirza, Suleyman Serdar Kozat
• ArXiv
• 2017

We investigate anomaly detection in an unsupervised framework and introduce Long Short Term Memory (LSTM) neural network based algorithms. In particular, given variable length data sequences, we… (More)

Online Training of LSTM Networks in Distributed Systems for Variable Length Data Sequences

• Tolga Ergen, Suleyman Serdar Kozat
• IEEE Transactions on Neural Networks and Learning…
• 2018

In this brief, we investigate online training of long short term memory (LSTM) architectures in a distributed network of nodes, where each node employs an LSTM-based structure for online regression.… (More)

An efficient bandit algorithm for general weight assignments

• Kaan Gokcesu, Tolga Ergen, Selami Çiftçi, Suleyman Serdar Kozat
• 25th Signal Processing and Communications…
• 2017

In this paper, we study the adversarial multi armed bandit problem and present a generally implementable efficient bandit arm selection structure. Since we do not have any statistical assumptions on… (More)

A highly efficient recurrent neural network architecture for data regression

• Tolga Ergen, Emir Ceyani
• 26th Signal Processing and Communications…
• 2018

In this paper, we study online nonlinear data regression and propose a highly efficient long short term memory (LSTM) network based architecture. Here, we also introduce on-line training algorithms… (More)

LEARNING BASED ON RECURRENT NEURAL NETWORKS FOR BIG DATA APPLICATIONS

• Tolga Ergen, Suleyman Serdar Kozat
• 2018

We study online training of Long Short Term Memory (LSTM) architectures in a network of nodes. For this framework, we first provide an LSTM based regression structure. To train this structure, we put… (More)

Online distributed nonlinear regression via neural networks

• Tolga Ergen, Suleyman Serdar Kozat
• 25th Signal Processing and Communications…
• 2017

In this paper, we study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture… (More)

A novel anomaly detection approach based on neural networks

• Tolga Ergen, Mine Kerpicci
• 26th Signal Processing and Communications…
• 2018

In this paper, we introduce a Long Short Term Memory (LSTM) networks based anomaly detection algorithm, which works in an unsupervised framework. We first introduce LSTM based structure for variable… (More)

A novel anomaly detection approach based on neural networks

• Tolga Ergen, Mine Kerpicci
• 2018

Recurrent neural networks based online learning algorithms for distributed systems

• Tolga Ergen, Safa Onur Sahin, Suleyman Serdar Kozat
• 26th Signal Processing and Communications…
• 2018

In this paper, we investigate online parameter learning for Long Short Term Memory (LSTM) architectures in distributed networks. Here, we first introduce an LSTM based structure for regression. Then,… (More)

• ‹
• 1
• 2
• ›