Search Results for author:
Found 36 papers, 22 papers with code
Samudra: An AI Global Ocean Emulator for Climate
AI emulators for forecasting have emerged as powerful tools that can outperform conventional numerical predictions.
Active learning for efficient discovery of optimal gene combinations in the combinatorial perturbation space
The advancement of novel combinatorial CRISPR screening technologies enables the identification of synergistic gene combinations on a large scale.
A Monte Carlo Framework for Calibrated Uncertainty Estimation in Sequence Prediction
In this paper, we propose a Monte Carlo framework to estimate probabilities and confidence intervals associated with the distribution of a discrete sequence.
Multi-modal AI for comprehensive breast cancer prognostication
Treatment selection in breast cancer is guided by molecular subtypes and clinical characteristics.
Understanding differences in applying DETR to natural and medical images
This study evaluates the applicability of these transformer-based design choices when applied to a screening mammography dataset that represents these distinct medical imaging data characteristics.
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling
Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data.
Quantifying Impairment and Disease Severity Using AI Models Trained on Healthy Subjects
We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients.
Sweetwater: An interpretable and adaptive autoencoder for efficient tissue deconvolution
Also, we demonstrate that Sweetwater effectively uncovers biologically meaningful patterns during the training process, increasing the reliability of the results.
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse
In particular, we discovered a systematic pattern that emerges when linear probing pre-trained models on downstream training data: the more feature collapse of pre-trained models on downstream training data, the higher the transfer accuracy.
Avoiding spurious correlations via logit correction
Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels.
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels.
Evaluating Unsupervised Denoising Requires Unsupervised Metrics
In this work, we propose two novel metrics: the unsupervised mean squared error (MSE) and the unsupervised peak signal-to-noise ratio (PSNR), which are computed using only noisy data.
Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning
The resulting representations and clusters from self-supervision are used as features of a survival model for recurrence prediction at the patient level.
PrimSeq: a deep learning-based pipeline to quantitate rehabilitation training
Here, we present PrimSeq, a pipeline to classify and count functional motions trained in stroke rehabilitation.
Deep Probability Estimation
Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty.
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions.
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.
Cramér-Rao bound-informed training of neural networks for quantitative MRI
We find, however, that in heterogeneous parameter spaces, i. e. in spaces in which the variance of the estimated parameters varies considerably, good performance is hard to achieve and requires arduous tweaking of the loss function, hyper parameters, and the distribution of the training data in parameter space.
Adaptive Denoising via GainTuning
Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets.
Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis
In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output, i. e. the location of a lesion.
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets.
Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
This shows that the network exploits global and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface.
Denoising
Materials Science
Image and Video Processing
Unsupervised Deep Video Denoising
This is advantageous because motion compensation is computationally expensive, and can be unreliable when the input data are noisy.
Ranked #5 on
Video Denoising
on Set8 sigma40
Deep Denoising For Scientific Discovery: A Case Study In Electron Microscopy
SBD outperforms existing techniques by a wide margin on a simulated benchmark dataset, as well as on real data.
An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department
In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time.
Early-Learning Regularization Prevents Memorization of Noisy Labels
In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization.
Ranked #5 on
Learning with noisy labels
on CIFAR-10N-Random2
Towards data-driven stroke rehabilitation via wearable sensors and deep learning
Thus, using a combination of IMU-based motion capture and deep learning, we were able to identify primitives automatically.
Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization
Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data.
On the design of convolutional neural networks for automatic detection of Alzheimer's disease
Early detection is a crucial goal in the study of Alzheimer's Disease (AD).
Interpretable and robust blind image denoising with bias-free convolutional neural networks
Here, however, we show that bias terms used in most CNNs (additive constants, including those used for batch normalization) interfere with the interpretability of these networks, do not help performance, and in fact prevent generalization of performance to noise levels not including in the training data.
Robust and interpretable blind image denoising via bias-free convolutional neural networks
In contrast, a bias-free architecture -- obtained by removing the constant terms in every layer of the network, including those used for batch normalization-- generalizes robustly across noise levels, while preserving state-of-the-art performance within the training range.
Data-driven Estimation of Sinusoid Frequencies
Frequency estimation is a fundamental problem in signal processing, with applications in radar imaging, underwater acoustics, seismic imaging, and spectroscopy.
Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems
In this work, we consider separable inverse problems, where the data are modeled as a linear combination of functions that depend nonlinearly on certain parameters of interest.
Time-Series Analysis via Low-Rank Matrix Factorization Applied to Infant-Sleep Data
We apply our methodology to detect anomalous individuals, to cluster the cohort into groups with different sleeping tendencies, and to obtain improved predictions of future sleep behavior.
A Learning-Based Framework for Line-Spectra Super-resolution
We propose a learning-based approach for estimating the spectrum of a multisinusoidal signal from a finite number of samples.
Multicompartment Magnetic Resonance Fingerprinting
Magnetic resonance fingerprinting (MRF) is a technique for quantitative estimation of spin-relaxation parameters from magnetic-resonance data.
Medical Physics Numerical Analysis Numerical Analysis Optimization and Control
