Neural Network Training with Highly Incomplete Datasets — mentioned by belter

Sat, 03 Jul 2021 15:00:40 GMT

"...we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets. First, the dataset is split into subsets of samples containing all values for a certain cluster of features. Then, these subsets are used to train individual neural networks. Finally, this ensemble of neural networks is combined into a single neural network whose training is fine-tuned using all complete datapoints. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer's disease pathology and…

Paper and discussion history. A mention is not an endorsement.

Neural Network Training with Highly Incomplete Datasets — HN submission

Sat, 03 Jul 2021 15:00:40 GMT

Neural Network Training with Highly Incomplete Datasets

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Neural Network Training with Highly Incomplete Datasets · HackerPapers discussions

Neural Network Training with Highly Incomplete Datasets — mentioned by belter

Neural Network Training with Highly Incomplete Datasets — HN submission