4 papers
Topic Segmentation Using Generative Language Models
Pierre Mackenzie, Maya Shah, Patrick Frenett
Topic segmentation using generative Large Language Models (LLMs) remains relatively unexplored. Previous methods use semantic similarity between sentences, but such models lack the…
Sparse Random Matrices for Dimensionality Reduction
Pierre Mackenzie
The Johnson-Lindenstrauss (JL) theorem states that a set of points in high-dimensional space can be embedded into a lower-dimensional space while approximately preserving pairwise…
Chord Recognition with Deep Learning
Pierre Mackenzie
Progress in automatic chord recognition has been slow since the advent of deep learning in the field. To understand why, I conduct experiments on existing methods and test hypothes…
CNNs for Style Transfer of Digital to Film Photography
Pierre Mackenzie, Mika Senghaas, Raphael Achddou
The use of deep learning in stylistic effect generation has seen increasing use over recent years. In this work, we use simple convolutional neural networks to model Cinestill800T…