Neural networks have been widely used for their ability to create generalized rulesets for a given set of training data. In applications where no such training data exists such as new video games, they are often overlooked ...

A recurrent convolutional neural network is supervised machine learning way to process images that has both properties of convolutional and recurrent networks. We propose Convolutional Neural Network (CNN) based approach ...

Presented is a deep learning based computational approach to solve the problem of enhancing the resolution of images gained from commonly available low magnification scanners, also known as the image super-resolution (SR) ...

We are working on the development of an adaptive learning framework addressing covariate shift, experienced in Behavioral Cloning (BC). BC user-modeling is a technique in which user-data, taken from observing a user’s ...

The phenomena of volatility decay (also known as time decay) and path dependence in leveraged exchange traded funds (ETF) markets have been documented in the literature. This dissertation examined whether it is possible ...

Many domain specific machine learning tasks require more fine tuning with respect to nondecomposable metrics to be effective. In many applications such as medical diagnosis and fraud detection, traditional loss measures ...

Accounting conservatism reflects the judgment and potential bias allowed per accrual-based accounting by choosing to disclose bad news ahead of holding a higher bar for reporting good news. Financial reporting aggressiveness ...

Training neural networks require sizeable datasets for meaningful output. It is difficult to acquire large datasets for many types of data. This is especially challenging for individuals and small organizations. We have ...

Organizational ambidexterity is a corporate strategy where a firm simultaneously seeks to pursue exploration and exploitation (March, 1991). Despite being described as one of the most interesting subjects in strategy ...