Search Results for author:
Found 24 papers, 12 papers with code
GPT-4 Technical Report
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
Ranked #1 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Learning correspondences of cardiac motion from images using biomechanics-informed modeling
Learning spatial-temporal correspondences in cardiac motion from images is important for understanding the underlying dynamics of cardiac anatomical structures.
Surrogate Gap Minimization Improves Sharpness-Aware Training
Instead, we define a \textit{surrogate gap}, a measure equivalent to the dominant eigenvalue of Hessian at a local minimum when the radius of the neighborhood (to derive the perturbed loss) is small.
Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
We demonstrate that ACProp has a convergence rate of $O(\frac{1}{\sqrt{T}})$ for the stochastic non-convex case, which matches the oracle rate and outperforms the $O(\frac{logT}{\sqrt{T}})$ rate of RMSProp and Adam.
Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity
Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain.
Multiple-shooting adjoint method for whole-brain dynamic causal modeling
Furthermore, MSA uses the adjoint method for accurate gradient estimation in the ODE; since the adjoint method is generic, MSA is a generic method for both linear and non-linear systems, and does not require re-derivation of the algorithm as in EM.
MALI: A memory efficient and reverse accurate integrator for Neural ODEs
Neural ordinary differential equations (Neural ODEs) are a new family of deep-learning models with continuous depth.
Ranked #19 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
AdaBelief Optimizer: Adapting Stepsizes by theBelief in Observed Gradients
We propose AdaBelief optimizer to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and training stability.
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
Viewing the exponential moving average (EMA) of the noisy gradient as the prediction of the gradient at the next time step, if the observed gradient greatly deviates from the prediction, we distrust the current observation and take a small step; if the observed gradient is close to the prediction, we trust it and take a large step.
Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis
We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders.
Neuropsychiatric Disease Classification Using Functional Connectomics -- Results of the Connectomics in NeuroImaging Transfer Learning Challenge
A second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing.
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
Neural ordinary differential equations (NODEs) have recently attracted increasing attention; however, their empirical performance on benchmark tasks (e. g. image classification) are significantly inferior to discrete-layer models.
2018 Robotic Scene Segmentation Challenge
In 2015 we began a sub-challenge at the EndoVis workshop at MICCAI in Munich using endoscope images of ex-vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models.
Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI
The addition of the generative model constrains the network to learn functional communities represented by the LSTM nodes that are both consistent with the data generation as well as useful for the classification task.
Decision Explanation and Feature Importance for Invertible Networks
We can determine the decision boundary of a linear classifier in the feature space; since the transform is invertible, we can invert the decision boundary from the feature space to the input space.
Ordinary differential equations on graph networks
Inspired by neural ordinary differential equation (NODE) for data in the Euclidean domain, we extend the idea of continuous-depth models to graph data, and propose graph ordinary differential equation (GODE).
Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
For the DA task, our DALACE model outperformed CycleGAN, TD-GAN , and DADR with DSC of 0. 847 compared to 0. 721, 0. 793 and 0. 806.
Graph Embedding Using Infomax for ASD Classification and Brain Functional Difference Detection
Here, we model the whole brain fMRI as a graph, which preserves geometrical and temporal information and use a Graph Neural Network (GNN) to learn from the graph-structured fMRI data.
Invertible Network for Classification and Biomarker Selection for ASD
Recently deep learning methods have achieved success in the classification task of ASD using fMRI data.
Graph Neural Network for Interpreting Task-fMRI Biomarkers
Our pipeline can be generalized to other graph feature importance interpretation problems.
Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery
Cooperative game theory is advantageous here because it directly considers the interaction between features and can be applied to any machine learning method, making it a novel, more accurate way of determining instance-wise biomarker importance from deep learning models.
ShelfNet for Fast Semantic Segmentation
Compared with real-time segmentation models such as BiSeNet, our model achieves higher accuracy at comparable speed on the Cityscapes Dataset, enabling the application in speed-demanding tasks such as street-scene understanding for autonomous driving.
Ranked #14 on
Semantic Segmentation
on PASCAL VOC 2012 test
LadderNet: Multi-path networks based on U-Net for medical image segmentation
A LadderNet has more paths for information flow because of skip connections and residual blocks, and can be viewed as an ensemble of Fully Convolutional Networks (FCN).
Ranked #6 on
Retinal Vessel Segmentation
on CHASE_DB1
Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI
Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier.
