Deep Learning Across Label Confidence Distribution via Transfer Learning
Offered By: Toronto Machine Learning Series (TMLS) via YouTube
Course Description
Overview
Explore a novel approach to deep learning called Filtered Transfer Learning (FTL) in this 35-minute conference talk from the Toronto Machine Learning Series. Discover how FTL addresses the challenge of training neural networks on datasets with varying levels of label confidence. Learn how this hierarchical fine-tuning process improves predictive power in noisy data systems by defining multiple tiers of data confidence as separate tasks in a transfer learning setting. Examine the application of FTL in predicting drug-protein interactions and understand its potential benefits for machine learning in fields like biology and medicine where large datasets often have uncertain labels. Gain insights into how this method can be applied to various domains, including radiological and histopathological image labeling and cancer drug resistance measurements.
Syllabus
Deep Learning Across Label Confidence Distribution via Transfer Learning
Taught by
Toronto Machine Learning Series (TMLS)
Related Courses
Structuring Machine Learning ProjectsDeepLearning.AI via Coursera Natural Language Processing on Google Cloud
Google Cloud via Coursera Introduction to Learning Transfer and Life Long Learning (3L)
University of California, Irvine via Coursera Advanced Deployment Scenarios with TensorFlow
DeepLearning.AI via Coursera Neural Style Transfer with TensorFlow
Coursera Project Network via Coursera