Robert (Munro) Monarch's Projects
Code for class on Deep Active Learning and Annotation
Coding exercise to extend tensorflow for imagenet to active learning, for use in a job interview or similar.
Coding exercise to extend to create an annotation tool for ImageNet labels on Machine Learning output
Practical example from Human-in-the-Loop Machine Learning book
Character-level Convolutional Neural Networks for text classification in PyTorch
Morphological parser for the Chichewa language
This dataset contains 25,000 messages drawn from events including an earthquake in Haiti in 2010, floods in Pakistan in 2010, super-storm Sandy in the U.S.A. in 2012, and news articles spanning a large number of years and 100s of different disasters. The data has been encoded with 38 different categories related to disaster response and has been stripped of messages with sensitive information in their entirety.
Deep Learning Course, example code
Practical example from Human-in-the-Loop Machine Learning book
human-in-the-loop synthetic data generation to augment the universal dependencies corpus with gender-balanced independent possessive pronouns
Practical example from Human-in-the-Loop Machine Learning book
Code for EMNLP2020 paper: "Detecting Independent Pronoun Bias with Partially-Synthetic DataGeneration"
Models built with TensorFlow
PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book
Use Deep Learning to Clone Driving Behavior
System to help volunteers manually parse information out of text messages.
NumPy implementations of common Active Learning strategies for Uncertainty Sampling
Generates an image for every unicode character