Similarity Search for Efficient Active Learning
We exploit this skew in large training datasets to reduce the number of unlabeled examples considered in each selection round with nearest nearest ...
similarity-search active-learning search semi-supervised-learning
Model Serving using FastAPI and Streamlit
Simple example of usage of streamlit and FastAPI for ML model serving.
fastapi streamlit image-segmentation deeplabv3
Pretraining for Joint Understanding of Textual and Tabular Data
bert pretraining natural-language-processing tabular-data
Adversarial Training Improves Product Discovery
Method automatically generates meaningful negative training examples for deep-learning model.
adversarial-learning adversarial-training product-discovery article
On the training dynamics of deep networks with L2 regularization
Role of L2 regularization in deep learning, and uncover simple relations between the performance of the model, the L2 coefficient, the learning rate, etc.
regularization l2 learning-rates l2-coefficient
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
Low-dimensional knowledge graph embeddings that simultaneously capture hierarchical relations and logical patterns.
knowledge-graphs graph-embedding graph-neural-networks acl-2020
The Simplest Way to Serve your NLP Model in Production w/ Python
From scikit-learn to Hugging Face Pipelines, learn the simplest way to deploy ML models using Ray Serve.
production ray huggingface scikit-learn
Debiased Contrastive Learning
We develop a debiased contrastive objective that corrects for the sampling of same-label data points, even without knowledge of the true labels.
contrastive-learning debiasing bias simclr
Bootstrap Your Own Latent (BYOL) in Pytorch
Practical implementation of a new state of the art (surpassing SimCLR) without contrast learning and having to designate negative pairs.
self-supervised-learning byol simclr code
projects 11 - 20 of 100
Share a project
Share something you or the community has made with ML.
Explore the latest
Join the community
Get feedback on your projects, interview prep, and more! Chat on Slack