Search Results for author:
Found 36 papers, 20 papers with code
Solving Inverse Problems with Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
A general framework for solving image inverse problems is introduced in this paper.
Classification with Scattering Operators
A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information.
Invariant Scattering Convolution Networks
A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification.
Deep Scattering Spectrum
A scattering transform defines a locally translation invariant representation which is stable to time-warping deformations.
Sound Information Theory Information Theory
Deep Learning by Scattering
We introduce general scattering transforms as mathematical models of deep neural networks with l2 pooling.
Wavelet methods for shape perception in electro-sensing
This paper aims at presenting a new approach to the electro-sensing problem using wavelets.
Generic Deep Networks with Wavelet Scattering
We introduce a two-layer wavelet scattering network, for object classification.
Rigid-Motion Scattering for Texture Classification
A rigid-motion scattering computes adaptive invariants along translations and rotations, with a deep convolutional network.
Unsupervised Deep Haar Scattering on Graphs
The classification of high-dimensional data defined on graphs is particularly difficult when the graph geometry is unknown.
Deep Roto-Translation Scattering for Object Classification
Dictionary learning algorithms or supervised deep convolution networks have considerably improved the efficiency of predefined feature representations such as SIFT.
Quantum Energy Regression using Scattering Transforms
We present a novel approach to the regression of quantum mechanical energies based on a scattering transform of an intermediate electron density representation.
Wavelet Scattering on the Pitch Spiral
We present a new representation of harmonic sounds that linearizes the dynamics of pitch and spectral envelope, while remaining stable to deformations in the time-frequency plane.
Understanding Deep Convolutional Networks
Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems.
Wavelet Scattering Regression of Quantum Chemical Energies
Sparse scattering regressions give state of the art results over two databases of organic planar molecules.
Inverse Problems with Invariant Multiscale Statistics
We propose a new approach to linear ill-posed inverse problems.
Computational Engineering, Finance, and Science
Multiscale Hierarchical Convolutional Networks
Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data.
Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory.
Generative networks as inverse problems with Scattering transforms
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood.
Phase Harmonic Correlations and Convolutional Neural Networks
For wavelet filters, we show numerically that signals having sparse wavelet coefficients can be recovered from few phase harmonic correlations, which provide a compressive representation
Statistical learning of geometric characteristics of wireless networks
To approximate (interpolate) the marking function, in our baseline approach, we build a statistical regression model of the marks with respect some local point distance representation.
Kymatio: Scattering Transforms in Python
The wavelet scattering transform is an invariant signal representation suitable for many signal processing and machine learning applications.
Deep Network Classification by Scattering and Homotopy Dictionary Learning
It is implemented in a deep convolutional network with a homotopy algorithm having an exponential convergence.
Maximum Entropy Models from Phase Harmonic Covariances
The covariance of a stationary process $X$ is diagonalized by a Fourier transform.
Particle gradient descent model for point process generation
This paper presents a statistical model for stationary ergodic point processes, estimated from a single realization observed in a square window.
Separation and Concentration in Deep Networks
On the opposite, a soft-thresholding on tight frames can reduce within-class variabilities while preserving class means.
Tight Frame Contractions in Deep Networks
Numerical experiments demonstrate that deep neural networks classifiers progressively separate class distributions around their mean, achieving linear separability.
Phase Collapse in Neural Networks
Spatial variability is therefore transformed into variability along channels.
Generalized Rectifier Wavelet Covariance Models For Texture Synthesis
State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN).
Scale Dependencies and Self-Similar Models with Wavelet Scattering Spectra
We introduce the wavelet scattering spectra which provide non-Gaussian models of time-series having stationary increments.
Wavelet Conditional Renormalization Group
We develop a multiscale approach to estimate high-dimensional probability distributions from a dataset of physical fields or configurations observed in experiments or simulations.
Learning multi-scale local conditional probability models of images
We instantiate this model using convolutional neural networks (CNNs) with local receptive fields, which enforce both the stationarity and Markov properties.
A Rainbow in Deep Network Black Boxes
Gaussian rainbow networks are defined with Gaussian weight distributions.
Conditionally Strongly Log-Concave Generative Models
There is a growing gap between the impressive results of deep image generative models and classical algorithms that offer theoretical guarantees.
Scattering Spectra Models for Physics
In this paper, we introduce scattering spectra models for stationary fields and we show that they provide accurate and robust statistical descriptions of a wide range of fields encountered in physics.
Path Shadowing Monte-Carlo
We introduce a Path Shadowing Monte-Carlo method, which provides prediction of future paths, given any generative model.
Generalization in diffusion models arises from geometry-adaptive harmonic representations
Finally, we show that when trained on regular image classes for which the optimal basis is known to be geometry-adaptive and harmonic, the denoising performance of the networks is near-optimal.
