Search Results for author:
Found 26 papers, 6 papers with code
Physics-Informed Boundary Integral Networks (PIBI-Nets): A Data-Driven Approach for Solving Partial Differential Equations
Partial differential equations (PDEs) can describe many relevant phenomena in dynamical systems.
Conditional Matrix Flows for Gaussian Graphical Models
Studying conditional independence among many variables with few observations is a challenging task.
Lagrangian Flow Networks for Conservation Laws
We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time.
Mesh-free Eulerian Physics-Informed Neural Networks
Physics-informed Neural Networks (PINNs) have recently emerged as a principled way to include prior physical knowledge in form of partial differential equations (PDEs) into neural networks.
Learning Invariances with Generalised Input-Convex Neural Networks
These networks represent functions that are guaranteed to have connected level sets forming smooth manifolds on the input space.
Learning Conditional Invariance through Cycle Consistency
We address these shortcomings with a novel approach to cycle consistency.
3DMolNet: A Generative Network for Molecular Structures
With the recent advances in machine learning for quantum chemistry, it is now possible to predict the chemical properties of compounds and to generate novel molecules.
On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures
The Neural Tangent Kernel (NTK) is an important milestone in the ongoing effort to build a theory for deep learning.
Inverse Learning of Symmetries
Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser.
Learning Extremal Representations with Deep Archetypal Analysis
The real-world applicability of the proposed method is demonstrated by exploring archetypes of female facial expressions while using multi-rater based emotion scores of these expressions as side information.
On the Difference Between the Information Bottleneck and the Deep Information Bottleneck
The actual mutual information consists of the lower bound which is optimised in DVIB and cognate models in practice and of two terms measuring how much the former requirement $T-X-Y$ is violated.
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts.
Regional Tree Regularization for Interpretability in Black Box Models
The lack of interpretability remains a barrier to the adoption of deep neural networks.
Deep Archetypal Analysis
"Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes.
Estimating Causal Effects With Partial Covariates For Clinical Interpretability
Estimating the causal effects of an intervention in the presence of confounding is a frequently occurring problem in applications such as medicine.
Informed MCMC with Bayesian Neural Networks for Facial Image Analysis
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.
Learning Sparse Latent Representations with the Deep Copula Information Bottleneck
Building on that, we show how this transformation translates to sparsity of the latent space in the new model.
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
The lack of interpretability remains a key barrier to the adoption of deep models in many applications.
Greedy Structure Learning of Hierarchical Compositional Models
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.
Causal Compression
We propose a new method of discovering causal relationships in temporal data based on the notion of causal compression.
Bayesian Markov Blanket Estimation
This paper considers a Bayesian view for estimating a sub-network in a Markov random field.
Probabilistic Clustering of Time-Evolving Distance Data
We present a novel probabilistic clustering model for objects that are represented via pairwise distances and observed at different time points.
Distance-Based Network Recovery under Feature Correlation
We present an inference method for Gaussian graphical models when only pairwise distances of n objects are observed.
Meta-Gaussian Information Bottleneck
We present a reformulation of the information bottleneck (IB) problem in terms of copula, using the equivalence between mutual information and negative copula entropy.
Bayesian Partitioning of Large-Scale Distance Data
A Bayesian approach to partitioning distance matrices is presented.
