Home      Library      Discussions      About
Join us

@idsia.ch

Mar 08, 2015
Logic in Computer Science

Containment for Conditional Tree Patterns

A Conditional Tree Pattern (CTP) expands an XML tree pattern with labels attached to the descendant edges. These labels can be XML element names or B…
May 27, 2018
Computer Vision
Artificial Intelligence

Deep Watershed Detector for Music Object Recognition

Optical Music Recognition (OMR) is an important and challenging area within music information retrieval, the accurate detection of music symbols in d…
Mar 27, 2018
Computer Vision
Machine Learning

DeepScores -- A Dataset for Segmentation, Detection and Classificatio…

We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object…
Aug 01, 2018
Artificial Intelligence
Logic in Computer Science

We introduced adjustment operators based on Lewis’ imaging functional, to deal with probabilistic inconsistent evidence, in a generalized setting of imprecise probabilities, specified by credal sets. These are summarized in Table 1. We point out tha…

Imaginary Kinematics

We introduce a novel class of adjustment rules for a collection of beliefs. This is an extension of Lewis' imaging to absorb probabilistic evidence i…
Jun 05, 2014
Artificial Intelligence
Machine Learning

Advances in Learning Bayesian Networks of Bounded Treewidth

This work presents novel algorithms for learning Bayesian network structures with bounded treewidth. Both exact and approximate methods are developed…
Nov 24, 2015
Data Structures and Algorithms

We showed that Configuration LP helps obtaining an algorithm with 1+ϵ capacity violation for uniform capacities. It remains open if a similar result is possible for general capacities. It seems that the difficulty of generalizing our algorithm to ge…

An approximation algorithm for Uniform Capacitated k-Median problem w…

We study the Capacitated k-Median problem, for which all the known constant factor approximation algorithms violate either the number of facilities o…
Sep 28, 2016
Machine Learning
Methodology

Statistical comparison of classifiers through Bayesian hierarchical …

Usually one compares the accuracy of two competing classifiers via null hypothesis significance tests (nhst). Yet the nhst tests suffer from importan…
Aug 09, 2019
Machine Learning
Statistics Theory

Probabilistic Models with Deep Neural Networks

Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has …
Aug 29, 2019
Machine Learning

InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

InferPy is a Python package for probabilistic modeling with deep neural networks. InferPy defines a user-friendly API which trades-off model complexi…
Jan 10, 2013
Data Structures and Algorithms

On Pairwise Spanners

Given an undirected $n$-node unweighted graph $G = (V, E)$, a spanner with stretch function $f(\cdot)$ is a subgraph $H\subseteq G$ such that, if two…
Aug 06, 2012
Data Structures and Algorithms

We have shown that the dependencies on the parameter k in the optimal time complexity of fixed-parameter algorithms for Vertex Cover and Split Vertex Deletion are essentially equal. This result can be considered as a tight bound on the time complexi…

On fixed-parameter algorithms for Split Vertex Deletion

In the Split Vertex Deletion problem, given a graph G and an integer k, we ask whether one can delete k vertices from the graph G to obtain a split g…
Aug 29, 2019
Machine Learning

InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

InferPy is a Python package for probabilistic modeling with deep neural networks. It defines a user-friendly API that trades-off model complexity wit…
Oct 05, 2020
Neural and Evolutionary Computation

Are Neural Nets Modular? Inspecting Functional Modularity Through D…

Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through ef…
Nov 27, 2020
Computation and Language
Artificial Intelligence
Machine Learning

For a first empirical validation of our pipeline we process, in a single run, two novels, namely Harry Potter and the Philosopher’s Stone (HP) by J. K. Rowling and Little Women (LW) by Louisa May Alcott. 1307 suitable sentences out of 32365 are iden…

Relation Clustering in Narrative Knowledge Graphs

When coping with literary texts such as novels or short stories, the extraction of structured information in the form of a knowledge graph might be h…
Jun 16, 2020
Machine Learning
Artificial Intelligence

Parameter-based Value Functions

Traditional off-policy actor-critic Reinforcement Learning (RL) algorithms learn value functions of a single target policy. However, when value funct…
Jul 06, 2012
Computer Vision
Neural and Evolutionary Computation

Multimodal similarity-preserving hashing

We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they bec…
May 21, 2013
Data Structures and Algorithms

Tight Kernel Bounds for Problems on Graphs with Small Degeneracy

In this paper we consider kernelization for problems on d-degenerate graphs, i.e. graphs such that any subgraph contains a vertex of degree at most $…
Feb 07, 2018
Artificial Intelligence

Efficient Learning of Bounded-Treewidth Bayesian Networks from Comple…

Learning a Bayesian networks with bounded treewidth is important for reducing the complexity of the inferences. We present a novel anytime algorithm …
May 14, 2007
Artificial Intelligence
Computer Vision

Multi-Dimensional Recurrent Neural Networks

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition.…
Aug 29, 2019
Machine Learning

InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy

InferPy is a Python package for probabilistic modeling with deep neural networks. InferPy defines a user-friendly API which trades-off model complexi…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description