
ChebyshevCantelli PACBayesBennett Inequality for the Weighted Majority Vote
We present a new secondorder oracle bound for the expected risk of a we...
read it

Information Bottleneck: Exact Analysis of (Quantized) Neural Networks
The information bottleneck (IB) principle has been suggested as a way to...
read it

Do EndtoEnd Speech Recognition Models Care About Context?
The two most common paradigms for endtoend speech recognition are conn...
read it

On Scaling Contrastive Representations for LowResource Speech Recognition
Recent advances in selfsupervised learning through contrastive training...
read it

Multimodal Variational Autoencoders for SemiSupervised Learning: In Defense of ProductofExperts
Multimodal generative models should be able to learn a meaningful latent...
read it

A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
To train Variational Autoencoders (VAEs) to generate realistic imagery r...
read it

On the convergence of the Metropolis algorithm with fixedorder updates for multivariate binary probability distributions
The Metropolis algorithm is arguably the most fundamental Markov chain M...
read it

The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A MultiInstitute Evaluation and Analysis Framework on a Standardized Dataset
Purpose: To organize a knee MRI segmentation challenge for characterizin...
read it

Labelsimilarity Curriculum Learning
Curriculum learning can improve neural network training by guiding the o...
read it

One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
Many recent medical segmentation systems rely on powerful deep learning ...
read it

UTime: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging
Neural networks are becoming more and more popular for the analysis of p...
read it

Knowledge distillation for semisupervised domain adaptation
In the absence of sufficient data variation (e.g., scanner and protocol ...
read it

On PACBayesian Bounds for Random Forests
Existing guarantees in terms of rigorous upper bounds on the generalizat...
read it

PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
For proper generalization performance of convolutional neural networks (...
read it

Training Big Random Forests with Little Resources
Without access to large compute clusters, building random forests on lar...
read it

Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy
Astrophysics and cosmology are rich with data. The advent of widearea d...
read it

A Strongly Quasiconvex PACBayesian Bound
We propose a new PACBayesian bound and a way of constructing a hypothes...
read it

Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
Largescale surveys make huge amounts of photometric data available. Bec...
read it

PopulationContrastiveDivergence: Does Consistency help with RBM training?
Estimating the loglikelihood gradient with respect to the parameters of...
read it

Recent Results on NoFreeLunch Theorems for Optimization
The sharpened NoFreeLunchtheorem (NFLtheorem) states that the perfor...
read it

Neutrality: A Necessity for SelfAdaptation
Selfadaptation is used in all main paradigms of evolutionary computatio...
read it

On Classes of Functions for which No Free Lunch Results Hold
In a recent paper it was shown that No Free Lunch results hold for any s...
read it
Christian Igel
is this you? claim profile