sent_debias
PaddleHelix
sent_debias | PaddleHelix | |
---|---|---|
1 | 1 | |
55 | 792 | |
- | 1.5% | |
0.0 | 5.4 | |
over 1 year ago | 2 months ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sent_debias
-
academic ethics issues in NLP
following on from the above, to what extent should we trust big models and the built in biases that they learn from huge scraped datasets? Many current SOTA trends for doing few shot learning on nlp tasks involve fine tuning existing large language models. There are lots of interesting research is going on around understanding and removing these biases like this paper from Liang and Li @ ACL2020. A related point is explainability - again some interesting work going on around things like rationale generation this now somewhat old paper by Lei et al 2016 gives some good context
PaddleHelix
-
Baidu and BioMap AI Research Open-Sources HelixFold-Single: An End-To-End MSA-Free Protein Structure Prediction Pipeline
Continue reading | Check out the paper and code.
What are some alternatives?
transferlearning - Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
dipy - DIPY is the paragon 3D/4D+ imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
typedb-ml - TypeDB-ML is the Machine Learning integrations library for TypeDB
DeBERTa - The implementation of DeBERTa
eirli - An Empirical Investigation of Representation Learning for Imitation (EIRLI), NeurIPS'21
Unsupervised-Classification - SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]