Tyler R. Scott

activity

20182022

most citedAdapted Deep Embeddings: A Synthesis of Methods for

k

-Shot Inductive Transfer Learning

48 citations · 58 across the 6 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021

von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning

Tyler R. Scott, Andrew C. Gallagher, Michael C. Mozer

Recent work has argued that classification losses utilizing softmax cross-entropy are superior not only for fixed-set classification tasks, but also by outperforming losses develop…

cs.LG2018★ 48 cited

Adapted Deep Embeddings: A Synthesis of Methods for $k$ -Shot Inductive Transfer Learning

Tyler R. Scott, Karl Ridgeway, Michael C. Mozer

The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to fa…

von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning

Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning

Adapted Deep Embeddings: A Synthesis of Methods for $k$ -Shot Inductive Transfer Learning