Nicole McNabb, Master’s candidate
David R. Cheriton School of Computer Science
Mohamed Malek Naouach, Master’s candidate
David R. Cheriton School of Computer Science
Carolyn Lamb, PhD candidate
David R. Cheriton School of Computer Science
This thesis is driven by the question of how computers can generate poetry, and how that poetry can be evaluated. We survey existing work on computer-generated poetry and interdisciplinary work on how to evaluate this type of computer-generated creative product.
Ifaz Kabir, Master’s candidate
David R. Cheriton School of Computer Science
Steven Wang, Master’s candidate
David R. Cheriton School of Computer Science
Yossef Musleh, Master’s candidate
David R. Cheriton School of Computer Science
We introduce a Monte Carlo randomized algorithm for computing the characteristic polynomial of a rank 2 Drinfeld module than runs in $O(n^2 \log n \log \log n \log q)$ field operations. We also introduce a deterministic algorithm that runs in $O(n^{2.6258} \log n + n^2 \log n \log log n \log q)$ field operations. Both approaches are a significant improvement over the current literature.
Elaheh Jalalpour, Master’s candidate
David R. Cheriton School of Computer Science
Ahmed Khan, Master’s candidate
David R. Cheriton School of Computer Science
Neurobiologically-plausible learning algorithms for recurrent neural networks that can perform supervised learning are a neglected area of study. Equilibrium propagation is a recent synthesis of several ideas in biological and artificial neural network research that uses a continuous-time, energy-based neural model with a local learning rule. However, despite dealing with recurrent networks, equilibrium propagation has only been applied to discriminative categorization tasks.
Angshuman Ghosh, Master’s candidate
David R. Cheriton School of Computer Science
Filip Pawlega, Master’s candidate
David R. Cheriton School of Computer Science