In this thesis, we study both theoretical and practical aspects of decision making, with a focus on reinforcement learning based methods. Reinforcement learning (RL) is a form of semi-supervised learning in which the agent ...

Deep neural network-based models have achieved unprecedented performance levels over many tasks in the traditional supervised setting and scale well with large quantities of data. On the other hand, improving performance ...

Abstract In recent years, deep neural networks have achieved extraordinary performance on supervised learning tasks. Convolutional neural networks (CNN) have vastly improved the state of the art for most computer vision ...

Compared to other models of data, the relational model offers several advantages: Clear separation between logical organization and physical storage of data Ease of understanding the logical structure Use of high-level ...

In this thesis, we propose and implement a multidimensional multilink system (MMS) architecture which uses message passing paradigm between computing elements (CEs). The merits of this architecture are its simplicity, regularity ...

In recent years, we have seen proliferation of computation-intensive, time-critical applications like real-time video, audio, IP-based telecommunication and so on. These applications offer value-added, nice-to-have features ...

The primary objective of this thesis is the formulation of a systematic procedure for the conversion of a Programmable Logic Array (PLA) having untestable faults into a corresponding completely testable PLA. In a completely ...

Decomposition-Based Approaches for Clearing Electronic Exchanges Electronic marketplaces have emerged in recent times as the backbone of important e-commerce and e-business applications to create efficient markets for ...

Software Maintenance is becoming more and more challenging due to rapidly changing customer needs, technologies and need for highly skilled labor. Many problems that existed a decade ago continue to exist or have even ...