David R. So
Microsoft (United States)(US)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Green IT and Sustainability, Evolutionary Algorithms and Applications, Machine Learning and Data Classification
Most-Cited Works
- → The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink(2022)267 cited
- → The Evolved Transformer(2019)196 cited
- → Carbon Emissions and Large Neural Network Training(2021)130 cited
- → AutoML-Zero: Evolving Machine Learning Algorithms From Scratch(2020)115 cited
- → Classification of crystallization outcomes using deep convolutional neural networks(2018)85 cited
- → MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records(2021)43 cited
- → Pay Attention to MLPs(2021)33 cited
- Searching for Efficient Transformers for Language Modeling(2021)
- → Transcending Scaling Laws with 0.1% Extra Compute(2023)26 cited