Machine Learning and Information Processing Laboratory

ConvDecoder

An un-trained neural network with a potential application in accelerated MRI

cs_deep_decoder

deep_inverse_book.github.io

DeepDeWedge

Self-supervised deep learning for denoising and missing wedge reconstruction of cryo-ET tomograms

early_stopping_double_descent

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

imaging_MLPs

overparameterized_convolutional_generators

Robustness-CS

Measuring the robustness of compressive sensing methods (including deep-learning-based ones) for image reconstruction.

transformers_for_imaging

ttt_for_deep_learning_cs

MLI-lab/ConvDecoder

An un-trained neural network with a potential application in accelerated MRI

MLI-lab/Robustness-CS

Measuring the robustness of compressive sensing methods (including deep-learning-based ones) for image reconstruction.

MLI-lab/DeepDeWedge

Self-supervised deep learning for denoising and missing wedge reconstruction of cryo-ET tomograms

MLI-lab/cs_deep_decoder

MLI-lab/transformers_for_imaging

MLI-lab/early_stopping_double_descent

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

MLI-lab/deep_inverse_book.github.io

MLI-lab/overparameterized_convolutional_generators

MLI-lab/ttt_for_deep_learning_cs

MLI-lab/imaging_MLPs

MLI-lab/cinemri

MLI-lab/noisy_dna_data_storage

Data recovery from millions of noisy reads

MLI-lab/sample_complexity_ss_recon

MLI-lab/candidate_training

Reproducible version of the experiments in "Leveraging inductive bias of neural networks for learning without explicit human annotations"

MLI-lab/recalibrating_conformal_prediction

QTC: Test-time recalibration of conformal predictors under distribution shift based on unlabeled examples

MLI-lab/Scaling_Laws_For_Deep_Learning_Based_Image_Reconstruction

MLI-lab/regularization_based_continual_learning

MLI-lab/robust_reconstructors_via_jittering

MLI-lab/channel_normalization

MLI-lab/imagenet_candidate_training

Training on noisy Flickr labels without annotators for better classification performance in ImageNet classification problem.

MLI-lab/monotonic_risk_relationships

MLI-lab/mri_data_diversity

MLI-lab/regularization-wise_double_descent