Learning new tricks from old dogs: Multi-source transfer learning from pre-trained networks
The advent of deep learning algorithms for mobile devices and sensors has led to a
dramatic expansion in the availability and number of systems trained on a wide range of …
dramatic expansion in the availability and number of systems trained on a wide range of …
Pass off fish eyes for pearls: Attacking model selection of pre-trained models
Selecting an appropriate pre-trained model (PTM) for a specific downstream task typically
requires significant efforts of fine-tuning. To accelerate this process, researchers propose …
requires significant efforts of fine-tuning. To accelerate this process, researchers propose …
Maximal Correlation Feature Selection and Suppression With Applications
JKW Lee - 2021 - dspace.mit.edu
In standard supervised learning, we assume that we are trying to learn some target variable
𝑌 from some data 𝑋. However, many learning problems can be framed as supervised …
𝑌 from some data 𝑋. However, many learning problems can be framed as supervised …