Search Results for author:
Found 22 papers, 4 papers with code
Approximating Families of Sharp Solutions to Fisher's Equation with Physics-Informed Neural Networks
Furthermore, a specific network architecture is studied which is tailored for solutions in the form of traveling waves.
Bringing Chemistry to Scale: Loss Weight Adjustment for Multivariate Regression in Deep Learning of Thermochemical Processes
We assess a simple, yet effective loss weight adjustment that outperforms the standard mean-squared error optimization and enables accurate learning of all species mass fractions, even of minor species where the standard optimization completely fails.
Finding the Optimum Design of Large Gas Engines Prechambers Using CFD and Bayesian Optimization
The turbulent jet ignition concept using prechambers is a promising solution to achieve stable combustion at lean conditions in large gas engines, leading to high efficiency at low emission levels.
Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory
Rate-distortion theory-based outlier detection builds upon the rationale that a good data compression will encode outliers with unique symbols.
Robust Bayesian Target Value Optimization
We consider the problem of finding an input to a stochastic black box function such that the scalar output of the black box function is as close as possible to a target value in the sense of the expected squared error.
FUNCK: Information Funnels and Bottlenecks for Invariant Representation Learning
Learning invariant representations that remain useful for a downstream task is still a key challenge in machine learning.
Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations.
On the Role of Fixed Points of Dynamical Systems in Training Physics-Informed Neural Networks
This paper empirically studies commonly observed training difficulties of Physics-Informed Neural Networks (PINNs) on dynamical systems.
Knock Detection in Combustion Engine Time Series Using a Theory-Guided 1D Convolutional Neural Network Approach
In addition, the model proved to classify knocking cycles in unseen engines with increased accuracy of 89% after adapting to their features via training on a small number of exclusively non-knocking cycles.
Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation
The introduced Constrained Markov Clustering (CoMaC) is an extension of a recent information-theoretic framework for (unsupervised) Markov aggregation to the semi-supervised case.
On the Pareto Front of Physics-Informed Neural Networks
We use the diffusion equation and Navier-Stokes equations in various test environments to analyze the effects of system parameters on the shape of the Pareto front.
Importance of feature engineering and database selection in a machine learning model: A case study on carbon crystal structures
In this work we seek to understand in depth the effect that the choice of features and the properties of the database have on a machine learning application.
Synwalk -- Community Detection via Random Walk Modelling
We thoroughly validate the effectiveness of our approach on synthetic and empirical networks, respectively, and compare Synwalk's performance with the performance of Infomap and Walktrap.
A Formally Robust Time Series Distance Metric
Distance-based classification is among the most competitive classification methods for time series data.
On Information Plane Analyses of Neural Network Classifiers -- A Review
Specifically, we argue that even in feed-forward neural networks the data processing inequality need not hold for estimates of mutual information.
SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder
We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and which is implemented in a typical Wasserstein auto-encoder framework.
Class-Conditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
We furthermore suggest a neural network where the decoder architecture is a parameterized naive Bayes decoder.
Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation
In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks.
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle
In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional.
Co-Clustering via Information-Theoretic Markov Aggregation
We present an information-theoretic cost function for co-clustering, i. e., for simultaneous clustering of two sets based on similarities between their elements.
Semi-supervised cross-entropy clustering with information bottleneck constraint
By combining the ideas from cross-entropy clustering (CEC) with those from the information bottleneck method (IB), our method trades between three conflicting goals: the accuracy with which the data set is modeled, the simplicity of the model, and the consistency of the clustering with side information.
Hard Clusters Maximize Mutual Information
In this paper, we investigate mutual information as a cost function for clustering, and show in which cases hard, i. e., deterministic, clusters are optimal.
