Mats L. Richter

According to our database, Mats L. Richter authored at least 19 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Simple and Scalable Strategies to Continually Pre-train Large Language Models.

Adam Ibrahim, Benjamin Thérien, Kshitij Gupta, Mats L. Richter, Quentin Gregory Anthony, Eugene Belilovsky, Timothée Lesort, Irina Rish

Trans. Mach. Learn. Res., 2024

CarbonSense: A Multimodal Dataset and Baseline for Carbon Flux Modelling.

Matthew Fortier, Mats L. Richter, Oliver Sonnentag, Chris Pal

CoRR, 2024

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models.

Pablo Pernias, Dominic Rampas, Mats L. Richter, Christopher Pal, Marc Aubreville

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Continual Pre-Training of Large Language Models: How to (re)warm your model?

Kshitij Gupta, Benjamin Thérien, Adam Ibrahim, Mats L. Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, Timothée Lesort

CoRR, 2023

Can Synthetic Images Improve CNN Performance in Wound Image Classification?

Leila Malihi, Ursula Hübner, Mats L. Richter, Maurice Moelleken, Mareike Przysucha, Dorothee Busch, Jan Heggemann, Guido Hafer, Stefan Wiemeyer, Gunther Heidemann, Joachim Dissemond, Cornelia Erfurt-Berge, Carlotta B. C. Barkhau, Achim Hendriks, Jens Hüsers

Proceedings of the Caring is Sharing - Exploiting the Value in Data for Health and Innovation - Proceedings of MIE 2023, Gothenburg, Sweden, 22, 2023

2022

Towards efficient convolutional neural architecture design: exploring the properties of neural architectures using spectral decomposition and logistic regression probes.

Mats L. Richter

PhD thesis, 2022

Delve: Neural Network Feature Variance Analysis.

Justin Shenk, Mats L. Richter, Wolf Byttner

J. Open Source Softw., 2022

Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance.

Mats L. Richter, Christopher Pal

CoRR, 2022

An Image Based Object Recognition System for Wound Detection and Classification of Diabetic Foot and Venous Leg Ulcers.

Jens Hüsers, Maurice Moelleken, Mats L. Richter, Mareike Przysucha, Leila Malihi, Dorothee Busch, Nina-Alexandra Götz, Jan Heggemann, Guido Hafer, Stefan Wiemeyer, Birgit Babitsch, Gunther Heidemann, Joachim Dissemond, Cornelia Erfurt-Berge, Ursula Hübner

Proceedings of the Challenges of Trustable AI and Added-Value on Health, 2022

Automatic Wound Type Classification with Convolutional Neural Networks.

Leila Malihi, Jens Hüsers, Mats L. Richter, Maurice Moelleken, Mareike Przysucha, Dorothee Busch, Jan Heggemann, Guido Hafer, Stefan Wiemeyer, Gunther Heidemann, Joachim Dissemond, Cornelia Erfurt-Berge, Ursula Hübner

Proceedings of the Advances in Informatics, Management and Technology in Healthcare, 2022

2021

Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis.

Mats L. Richter, Julius Schöning, Ulf Krumnack

CoRR, 2021

Exploring the Properties and Evolution of Neural Network Eigenspaces during Training.

Mats L. Richter, Leila Malihi, Anne-Kathrin Patricia Windler, Ulf Krumnack

CoRR, 2021

Size Matters.

Mats L. Richter, Wolf Byttner, Ulf Krumnack, Ludwig Schallner, Justin Shenk

CoRR, 2021

Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training.

Mats L. Richter, Julius Schöning, Anna Wiedenroth, Ulf Krumnack

Proceedings of the 20th IEEE International Conference on Machine Learning and Applications, 2021

(Input) Size Matters for CNN Classifiers.

Mats L. Richter, Wolf Byttner, Ulf Krumnack, Anna Wiedenroth, Ludwig Schallner, Justin Shenk

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2021, 2021

AI-Based Crop Rotation for Sustainable Agriculture Worldwide.

Julius Schöning, Mats L. Richter

Proceedings of the IEEE Global Humanitarian Technology Conference, 2021

Feature Space Saturation during Training.

Mats L. Richter, Justin Shenk, Wolf Byttner, Anna Wiedenroth, Mikael Huss

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020

Feature Space Saturation during Training.

Justin Shenk, Mats L. Richter, Wolf Byttner, Anders Arpteg, Mikael Huss

CoRR, 2020

2019

Spectral Analysis of Latent Representations.

Justin Shenk, Mats L. Richter, Anders Arpteg, Mikael Huss

CoRR, 2019