
AWD3: Dynamic Reduction of the Estimation Bias
Valuebased deep Reinforcement Learning (RL) algorithms suffer from the ...
read it

OffPolicy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay
The experience replay mechanism allows agents to use the experiences mul...
read it

ParameterFree Deterministic Reduction of the Estimation Bias in Continuous Control
Approximation of the value functions in valuebased deep reinforcement l...
read it

Estimation Error Correction in Deep Reinforcement Learning for Deterministic ActorCritic Methods
In valuebased deep reinforcement learning methods, approximation of val...
read it

PySAD: A Streaming Anomaly Detection Framework in Python
PySAD is an opensource python framework for anomaly detection on stream...
read it

MultiLabel Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
We investigate crosslingual sentiment analysis, which has attracted sig...
read it

Spatiotemporal Sequence Prediction with Point Processes and Selforganizing Decision Trees
We investigate spatiotemporal prediction and introduce a novel predicti...
read it

A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data
We investigate regression for variable length sequential data containing...
read it

Achieving Online Regression Performance of LSTMs with Simple RNNs
Recurrent Neural Networks (RNNs) are widely used for online regression d...
read it

Unsupervised Anomaly Detection via Deep Metric Learning with EndtoEnd Optimization
We investigate unsupervised anomaly detection for highdimensional data ...
read it

RNNbased Online Learning: An Efficient FirstOrder Optimization Algorithm with a Convergence Guarantee
We investigate online nonlinear regression with continually running recu...
read it

Stability of the Decoupled Extended Kalman Filter Learning Algorithm in LSTMBased Online Learning
We investigate the convergence and stability properties of the decoupled...
read it

Stability of the Decoupled Extended Kalman Filter in the LSTMBased Online Learning
We investigate the convergence and stability properties of the decoupled...
read it

Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
We investigate the adversarial bandit problem with multiple plays under ...
read it

An Efficient EKF Based Algorithm For LSTMBased Online Learning
We investigate online nonlinear regression with long short term memory (...
read it

Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under SubGradient Observation Failures
We study online convex optimization under stochastic subgradient observ...
read it

Efficient Implementation Of NewtonRaphson Methods For Sequential Data Prediction
We investigate the problem of sequential linear data prediction for real...
read it

Data Imputation through the Identification of Local Anomalies
We introduce a comprehensive and statistical framework in a model free s...
read it

Predicting Nearly As Well As the Optimal Twice Differentiable Regressor
We study nonlinear regression of real valued data in an individual seque...
read it

A Comprehensive Approach to Universal Piecewise Nonlinear Regression Based on Trees
In this paper, we investigate adaptive nonlinear regression and introduc...
read it

A Novel Training Algorithm for HMMs with Partial and Noisy Access to the States
This paper proposes a new estimation algorithm for the parameters of an ...
read it
Suleyman S. Kozat
is this you? claim profile