research
∙
08/08/2023
Continual Pre-Training of Large Language Models: How to (re)warm your model?
Large language models (LLMs) are routinely pre-trained on billions of to...
share
research
∙
11/26/2022
Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance
Minimal changes to neural architectures (e.g. changing a single hyperpar...
research
∙
06/23/2021
Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
Applying artificial neural networks (ANN) to specific tasks, researchers...
research
∙
06/17/2021
Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
In this work we explore the information processing inside neural network...
research
∙
02/02/2021
Size Matters
Fully convolutional neural networks can process input of arbitrary size ...
research
∙
06/15/2020
Feature Space Saturation during Training
We propose layer saturation - a simple, online-computable method for ana...
research
∙
07/19/2019