arxivst stuff from arxiv that you should probably bookmark

Linearly Scale Streaming Data Models

Streaming in your dataset? This paper might help you scale your runtime, prune redundant features and avoid local minima.

distributed learning streaming covariance-fitting

Using Bag Similarity and Transfer Learning for Improved Generalization

The authors address the problem of transfer learning between medical images collected from different imaging scanners. First they train multiple models across different scanners then at evaluation time a weighted ensemble is constructed according to the distance between train and test images. Of the three distance methods evaluated in the paper, bag similarity had the best performance on brain tissue segmentation.

medicine image segmentation transfer learning

New State-of-the-Art for Few-Shot Learning

Prototypical networks achieve a new state of the art on zero-shot classification (inference on unseen classes) on the CU-Birds dataset and one-shot classification (learning from just a few examples per class) on the Omniglot dataset.

state-of-the-art one-shot zero-shot learning

State Of The Art Results

New Datasets

Recent Abstracts