Search Results for author:
Found 12 papers, 3 papers with code
Learnable Group Transform For Time-Series
This framework allows us to generalize classical time-frequency transformations such as the Wavelet Transform, and to efficiently learn the representation of signals.
Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation
We obtain in closed form (i) the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and (ii) the partition and per-region affine mappings of the per-layer feedforward networks.
The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning
Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in domains with limited labels.
Toward a Geometrical Understanding of Self-supervised Contrastive Learning
When used for transfer learning, the projector is discarded since empirical results show that its representation generalizes more poorly than the encoder's.
Spatial Transformer K-Means
This enables (i) the reduction of intrinsic nuisances associated with the data, reducing the complexity of the clustering task and increasing performances and producing state-of-the-art results, (ii) clustering in the input space of the data, leading to a fully interpretable clustering algorithm, and (iii) the benefit of convergence guarantees.
Interpretable Image Clustering via Diffeomorphism-Aware K-Means
We design an interpretable clustering algorithm aware of the nonlinear structure of image manifolds.
Sparse Multi-Family Deep Scattering Network
The SMF-DSN enhances the DSN by (i) increasing the diversity of the scattering coefficients and (ii) improves its robustness with respect to non-stationary noise.
Nonlinear Regression with a Convolutional Encoder-Decoder for Remote Monitoring of Surface Electrocardiograms
We will achieve this goal with 12-lead ECG reconstruction and by providing a new diagnostic tool for classifying atypical heartbeats.
Deep Autoencoders: From Understanding to Generalization Guarantees
Our regularizations leverage recent advances in the group of transformation learning to enable AEs to better approximate the data manifold without explicitly defining the group underlying the manifold.
The Geometry of Deep Networks: Power Diagram Subdivision
The subdivision process constrains the affine maps on the (exponentially many) power diagram regions to greatly reduce their complexity.
Spline Filters For End-to-End Deep Learning
We propose to tackle the problem of end-to-end learning for raw waveform signals by introducing learnable continuous time-frequency atoms.
Overcomplete Frame Thresholding for Acoustic Scene Analysis
In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization.
