Search Results for author:
Found 27 papers, 9 papers with code
A Compressed Sensing Framework for Magnetic Resonance Fingerprinting
Inspired by the recently proposed Magnetic Resonance Fingerprinting (MRF) technique, we develop a principled compressed sensing framework for quantitative MRI.
Information Theory Information Theory
Dictionary learning for fast classification based on soft-thresholding
The dictionary learning problem, which jointly learns the dictionary and linear classifier, is cast as a difference of convex (DC) program and solved efficiently with an iterative DC solver.
Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results
With a moderate but well-defined assumption, we prove that the SNN indeed solves sparse coding.
PAC-Bayesian Margin Bounds for Convolutional Neural Networks
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers.
Cheap DNN Pruning with Performance Guarantees
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers often with little or no drop in classification accuracy.
FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy.
Improved Breast Mass Segmentation in Mammograms with Conditional Residual U-net
We explore the use of deep learning for breast mass segmentation in mammograms.
CoverBLIP: accelerated and scalable iterative matched-filtering for Magnetic Resonance Fingerprint reconstruction
Current popular methods for Magnetic Resonance Fingerprint (MRF) recovery are bottlenecked by the heavy computations of a matched-filtering step due to the growing size and complexity of the fingerprint dictionaries in multi-parametric quantitative MRI applications.
Revisiting hard thresholding for DNN pruning
Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy degradation and possibly less retraining time.
The role of invariance in spectral complexity-based generalization bounds
Deep convolutional neural networks (CNNs) have been shown to be able to fit a random labeling over data while still being able to generalize well for normal labels.
The Practicality of Stochastic Optimization in Imaging Inverse Problems
We investigate this phenomenon and propose a theory-inspired mechanism for the practitioners to efficiently characterize whether it is beneficial for an inverse problem to be solved by stochastic optimization techniques or not.
Compressive MRI quantification using convex spatiotemporal priors and deep auto-encoders
We propose a dictionary-matching-free pipeline for multi-parametric quantitative MRI image computing.
SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization
We introduce SPRING, a novel stochastic proximal alternating linearized minimization algorithm for solving a class of non-smooth and non-convex optimization problems.
Image Deconvolution
Stochastic Optimization
Optimization and Control
90C26
Neuromorphic Nearest-Neighbor Search Using Intel's Pohoiki Springs
Neuromorphic computing applies insights from neuroscience to uncover innovations in computing technology.
The Neural Tangent Link Between CNN Denoisers and Non-Local Filters
While the NTK theory accurately predicts the filter associated with networks trained using standard gradient descent, our analysis shows that it falls short to explain the behaviour of networks trained using the popular Adam optimizer.
A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems
In this work we propose an efficient stochastic plug-and-play (PnP) algorithm for imaging inverse problems.
One Bit to Rule Them All : Binarizing the Reconstruction in 1-bit Compressive Sensing
This work focuses on the reconstruction of sparse signals from their 1-bit measurements.
Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware.
Efficient Neuromorphic Signal Processing with Loihi 2
The biologically inspired spiking neurons used in neuromorphic computing are nonlinear filters with dynamic state variables -- very different from the stateless neuron models used in deep learning.
Unsupervised Learning From Incomplete Measurements for Inverse Problems
In many real-world inverse problems, only incomplete measurement data are available for training which can pose a problem for learning a reconstruction function.
Sensing Theorems for Unsupervised Learning in Linear Inverse Problems
In this paper, we present necessary and sufficient sensing conditions for learning the signal model from measurement data alone which only depend on the dimension of the model and the number of operators or properties of the group action that the model is invariant to.
Imaging with Equivariant Deep Learning
From early image processing to modern computational imaging, successful models and algorithms have relied on a fundamental property of natural signals: symmetry.
The Intel Neuromorphic DNS Challenge
A critical enabler for progress in neuromorphic computing research is the ability to transparently evaluate different neuromorphic solutions on important tasks and to compare them to state-of-the-art conventional solutions.
NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings.
Efficient Video and Audio processing with Loihi 2
Loihi 2 is an asynchronous, brain-inspired research processor that generalizes several fundamental elements of neuromorphic architecture, such as stateful neuron models communicating with event-driven spikes, in order to address limitations of the first generation Loihi.
Self-Supervised Learning for Image Super-Resolution and Deblurring
These methods critically rely on invariance to translations and/or rotations of the image distribution to learn from incomplete measurement data alone.
Perspective-Equivariant Imaging: an Unsupervised Framework for Multispectral Pansharpening
Ill-posed image reconstruction problems appear in many scenarios such as remote sensing, where obtaining high quality images is crucial for environmental monitoring, disaster management and urban planning.
