rmunro

active_learning_class

Code for class on Deep Active Learning and Annotation

active_learning_imagenet

Coding exercise to extend tensorflow for imagenet to active learning, for use in a job interview or similar.

annotation_imagenet

Coding exercise to extend to create an annotation tool for ImageNet labels on Machine Learning output

bicycle_detection

Practical example from Human-in-the-Loop Machine Learning book

disaster_response_messages

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.

headlines

Practical example from Human-in-the-Loop Machine Learning book

pytorch_active_learning

PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book

uncertainty_sampling_numpy

NumPy implementations of common Active Learning strategies for Uncertainty Sampling

unicode_image_generator

Generates an image for every unicode character

UD_English-Pronouns

rmunro/pytorch_active_learning

PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book

rmunro/active_learning_imagenet

Coding exercise to extend tensorflow for imagenet to active learning, for use in a job interview or similar.

rmunro/uncertainty_sampling_numpy

NumPy implementations of common Active Learning strategies for Uncertainty Sampling

rmunro/unicode_image_generator

Generates an image for every unicode character

rmunro/active_learning_class

Code for class on Deep Active Learning and Annotation

rmunro/disaster_response_messages

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.

rmunro/headlines

Practical example from Human-in-the-Loop Machine Learning book

rmunro/annotation_imagenet

Coding exercise to extend to create an annotation tool for ImageNet labels on Machine Learning output

rmunro/bicycle_detection

Practical example from Human-in-the-Loop Machine Learning book

rmunro/food_safety

Practical example from Human-in-the-Loop Machine Learning book

rmunro/deep_learning_course

rmunro/char-cnn-text-classification-pytorch

Character-level Convolutional Neural Networks for text classification in PyTorch

rmunro/chichewa

Morphological parser for the Chichewa language

rmunro/gender_augmentation

human-in-the-loop synthetic data generation to augment the universal dependencies corpus with gender-balanced independent possessive pronouns

rmunro/models

Models built with TensorFlow

rmunro/SMS-Turks

System to help volunteers manually parse information out of text messages.

rmunro/dl-dataday-workshop

Deep Learning Course, example code

rmunro/masked_bias_detection

Code for EMNLP2020 paper: "Detecting Independent Pronoun Bias with Partially-Synthetic DataGeneration"

rmunro/SDCND-Behavioral-Cloning-P3

Use Deep Learning to Clone Driving Behavior