• Stars
    star
    15
  • Rank 1,371,379 (Top 28 %)
  • Language
    Jupyter Notebook
  • Created over 4 years ago
  • Updated over 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code for reproducing figures and results in the paper ``Early stopping in deep networks: Double descent and how to eliminate it''

More Repositories

1

ConvDecoder

An un-trained neural network with a potential application in accelerated MRI
Jupyter Notebook
39
star
2

Robustness-CS

Measuring the robustness of compressive sensing methods (including deep-learning-based ones) for image reconstruction.
Jupyter Notebook
28
star
3

DeepDeWedge

Self-supervised deep learning for denoising and missing wedge reconstruction of cryo-ET tomograms
Jupyter Notebook
26
star
4

cs_deep_decoder

Jupyter Notebook
17
star
5

transformers_for_imaging

Jupyter Notebook
16
star
6

overparameterized_convolutional_generators

Jupyter Notebook
14
star
7

ttt_for_deep_learning_cs

Jupyter Notebook
14
star
8

deep_inverse_book.github.io

Jupyter Notebook
13
star
9

imaging_MLPs

Jupyter Notebook
8
star
10

noisy_dna_data_storage

Data recovery from millions of noisy reads
Jupyter Notebook
6
star
11

cinemri

Python
6
star
12

sample_complexity_ss_recon

Jupyter Notebook
4
star
13

recalibrating_conformal_prediction

QTC: Test-time recalibration of conformal predictors under distribution shift based on unlabeled examples
Jupyter Notebook
3
star
14

candidate_training

Reproducible version of the experiments in "Leveraging inductive bias of neural networks for learning without explicit human annotations"
Jupyter Notebook
3
star
15

robust_reconstructors_via_jittering

Python
2
star
16

regularization_based_continual_learning

Jupyter Notebook
2
star
17

Scaling_Laws_For_Deep_Learning_Based_Image_Reconstruction

Jupyter Notebook
2
star
18

monotonic_risk_relationships

Jupyter Notebook
1
star
19

channel_normalization

Jupyter Notebook
1
star
20

imagenet_candidate_training

Training on noisy Flickr labels without annotators for better classification performance in ImageNet classification problem.
Jupyter Notebook
1
star