Browsing by Author "Mirza, Ali Hassan"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Low complexity efficient online learning algorithms using LSTM networks(Bilkent University, 2018-12) Mirza, Ali HassanIn this thesis, we implement efficient online learning algorithms using the Long Short Term Memory (LSTM) networks with low time and computational complexity. In Chapter 2, we investigate efficient covariance information-based online learning using the LSTM networks known as Co-LSTM networks. We utilize the covariance information into the LSTM gating structure and propose various effi- cient models. We reduce the computational complexity by applying the Weight Matrix Factorization (WMF) trick and derive the additive gradient based updates. In Chapter 3, we give a practical application of the network intrusion detection using the Co-LSTM networks. In Chapter 4, we propose a boosted binary version of Tree-LSTM networks which we call BBT-LSTM networks. We introduce the depth and windowing factor into the N-ary Tree-LSTM networks where each LSTM node is binarily split and the whole tree architecture grows in a balanced manner. In order to reduce the computational complexity of the BBT-LSTM networks, we apply WMF trick, replace the regular multiplication operator with the energy efficient operator and finally introduce the slicing operation on the BBT-LSTM network weight matrices. In Chapter 5, we propose another low complexity LSTM network based on a minimum number of hopping over the input data sequence. We study two methods to select the appropriate value of the hopping distance. Through an extensive set of experiments using the real-life data sets, we demonstrate the significant increase in the performance of the proposed algorithms at the end of each chapter.Item Open Access Online optimization of wireless sensors selection over an unknown stochastic environment(Institute of Electrical and Electronics Engineers, 2018) Qureshi, Muhammad Anjum; Sarmad, Wardah; Noor, Hira; Mirza, Ali HassanWireless communication is considered to be more challenging than the typical wired communication due to unpredictable channel conditions. In this paper, we target coverage area problem, where a group of sensors is selected from a set of sensors placed in a particular area to maximize the coverage provided to that area. The constraints to this optimization are the battery power of the sensor and number of sensors that are active at a given time. We consider a variant of the coverage related to a particular sensor, where coverage is considered to be an unknown stochastic variable, and hence, we need to learn the best subset of sensors in real time. We propose an online combinatorial optimization algorithm based on multi-armed bandits framework that learns the expected best subset of sensors, and the regret of the proposed online algorithm is sub-linear in time. The achieved performance proves the robustness and effectiveness of the proposed online algorithm in wireless sensor selection over an unknown stochastic environment.