Search
Now showing items 101-108 of 108
Deep representation learning on hypersphere
(Georgia Institute of Technology, 2020-07-27)
How to efficiently learn discriminative deep features is arguably one of the core problems in deep learning, since it can benefit a lot of downstream tasks such as visual recognition, object detection, semantic segmentation, ...
Large scale machine learning for geospatial problems in computational sustainability
(Georgia Institute of Technology, 2020-05-14)
The UN laid out 17 Sustainable Development Goals as part of the “The 2030 Agenda for Sustainable Development”. Each goal consists of broad targets - such as increasing the percentage of forested land (indicator 15.1.1) - ...
FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or ...
Snow Coverage Prediction using Machine Learning Techniques
Snow coverage is often predicted through analysis of satellite images. Two of the most common satellites used for predictions are MODIS and Landsat. Unfortunately, snow coverage predictions are limited either by MODIS ...
On Formula Embeddings in Neural-Guided SAT Solving
Branching heuristics determine the performance of search-based SAT solvers. We note that recently, Neural Machine Learning approaches have been proposed to learn such heuristics from data. The first step in learning a ...
Productize ML: A Machine Learning in Production Course
(Georgia Institute of Technology, 2020-08)
This document presents the project paper for the CS6460 course for which a Content track was chosen to teach a Machine Learning in Production course using Cognitive Emotional Pedagogy and Distance learning and framed around ...
Interactive Scalable Interfaces for Machine Learning Interpretability
(Georgia Institute of Technology, 2020-12-01)
Data-driven paradigms now solve the world's hardest problems by automatically learning from data. Unfortunately, what is learned is often unknown to both the people who train the models and the people they impact. This has ...
Prokaryotic Gene Start Prediction: Algorithms for Genomes and Metagenomes
(Georgia Institute of Technology, 2020-12-01)
Prokaryotic gene-prediction is the task of finding genes in archaeal or bacterial DNA sequences. These genomes consist of alternating gene-coding and non-coding regions, meaning the task is solved by determining the start ...