
Recurrent Connectivity Aids Recognition of Partly Occluded Objects
Feedforward convolutional neural networks are the prevalent model of cor...
read it

Learning in Competitive Network with Haeusslers Equation adapted using FIREFLY algorithm
Many of the competitive neural network consists of spatially arranged ne...
read it

Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders
Recurrent connections in the visual cortex are thought to aid object rec...
read it

Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning
In this paper, we tackle an open research question in transfer learning,...
read it

Simulated Autonomous Driving on Realistic Road Networks using Deep Reinforcement Learning
Using Deep Reinforcement Learning (DRL) can be a promising approach to h...
read it

Building effective deep neural network architectures one feature at a time
Successful training of convolutional neural networks is often associated...
read it

A Recurrent Neural Model with Attention for the Recognition of Chinese Implicit Discourse Relations
We introduce an attentionbased BiLSTM for Chinese implicit discourse r...
read it

Combinational neural network using Gabor filters for the classification of handwritten digits
A classification algorithm that combines the components of knearest nei...
read it

Attractor Metadynamics in Adapting Neural Networks
Slow adaption processes, like synaptic and intrinsic plasticity, abound ...
read it

Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences
Traditionally, pose estimation is considered as a two step problem. Firs...
read it

Artificial general intelligence through recursive data compression and grounded reasoning: a position paper
This paper presents a tentative outline for the construction of an artif...
read it

Model Validation for Vision Systems via Graphics Simulation
Rapid advances in computation, combined with latest advances in computer...
read it

Simulations for Validation of Vision Systems
As the computer vision matures into a systems science and engineering di...
read it

Emotional control  conditio sine qua non for advanced artificial intelligences?
Humans dispose of two intertwined information processing pathways, cogni...
read it

Modeling sequential data using higherorder relational features and predictive training
Bilinear feature learning models, like the gated autoencoder, were prop...
read it

Learning to relate images: Mapping units, complex cells and simultaneous eigenspaces
A fundamental operation in many vision tasks, including motion understan...
read it

Unsupervised learning of depth and motion
We present a model for the joint estimation of disparity and motion. The...
read it

Bayesian multitask inverse reinforcement learning
We generalise the problem of inverse reinforcement learning to multiple ...
read it

Closedform EM for Sparse Coding and its Application to Source Separation
We define and discuss the first sparse coding algorithm based on closed...
read it

Autonomous Cleaning of Corrupted Scanned Documents  A Generative Modeling Approach
We study the task of cleaning scanned text documents that are strongly c...
read it

Determining a rotation of a tetrahedron from a projection
The following problem, arising from medical imaging, is addressed: Suppo...
read it

On the Number of ManytoMany Alignments of Multiple Sequences
We count the number of alignments of N > 1 sequences when matchup types...
read it

When is a polynomial ideal binomial after an ambient automorphism?
Can an ideal I in a polynomial ring k[x] over a field be moved by a chan...
read it

The LCSC cluster: greenest supercomputer in the world in Green500 list of November 2014
The LCSC (Lattice Computer for Scientific Computing) is a general purpo...
read it

The satisfiability threshold for random linear equations
Let A be a random m× n matrix over the finite field F_q with precisely k...
read it

Dynamic Pricing in Competitive Markets
Dynamic pricing of goods in a competitive environment to maximize revenu...
read it

Space Improvements and Equivalences in a Functional Core Language
We explore space improvements in LRP, a polymorphically typed callbyne...
read it

The replica symmetric phase of random constraint satisfaction problems
Random constraint satisfaction problems play an important role in comput...
read it

Optimization over the Boolean Hypercube via Sums of Nonnegative Circuit Polynomials
Various key problems from theoretical computer science can be expressed ...
read it

Efficient BlackBox Reductions for Separable Cost Sharing
In cost sharing games with delays, a set of agents jointly allocates a f...
read it

Greedy can also beat pure dynamic programming
Many dynamic programming algorithms are "pure" in that they only use min...
read it

Tracing Equilibrium in Dynamic Markets via Distributed Adaptation
Competitive equilibrium is a central concept in economics with numerous ...
read it

MaxProduct for Maximum Weight Matching  Revisited
We focus on belief propagation for the assignment problem, also known as...
read it

On Fair Division of Indivisible Items
We consider the task of assigning indivisible goods to a set of agents i...
read it

Greedy can beat pure dynamic programming
Many dynamic programming algorithms for discrete 01 optimizationproblem...
read it

Estimation of Covariance Matrices for Portfolio Optimization using Gaussian Processes
Estimating covariances between financial assets plays an important role ...
read it

ResourceSize matters: Improving Neural Named Entity Recognition with Optimized Large Corpora
This study improves the performance of neural named entity recognition b...
read it

The rank of random matrices over finite fields
We determine the rank of a random matrix A over a finite field with pres...
read it

Packing Returning Secretaries
We study online secretary problems with returns in combinatorial packing...
read it

The LCSC cluster: Optimizing power efficiency to become the greenest supercomputer in the world in the Green500 list of November 2014
The LCSC (Lattice Computer for Scientific Computing) is a general purpo...
read it

Rethinking Layerwise Feature Amounts in Convolutional Neural Network Architectures
We characterize convolutional neural networks with respect to the relati...
read it

Lower bounds on the chromatic number of random graphs
We prove that a formula predicted on the basis of nonrigorous physics a...
read it

Bivariate change point detection: joint detection of changes in expectation and variance
A method for change point detection is proposed. In a sequence of indepe...
read it

DistanceNet: Estimating Traveled Distance from Monocular Images using a Recurrent Convolutional Neural Network
Classical monocular vSLAM/VO methods suffer from the scale ambiguity pro...
read it

Network Investment Game with Wardrop Followers
We study a twosided network investment game consisting of two sets of p...
read it

Efficiently Generating Geometric Inhomogeneous and Hyperbolic Random Graphs
Hyperbolic random graphs (HRG) and geometric inhomogeneous random graphs...
read it

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
We introduce a unified probabilistic approach for deep continual learnin...
read it

The rank of sparse random matrices
Generalising prior work on the rank of random matrices over finite field...
read it

A Stable Boundary Integral Formulation of an Acoustic Wave Transmission Problem with Mixed Boundary Conditions
In this paper, we consider an acoustic wave transmission problem with mi...
read it

On stable invertibility and global Newton convergence for convex monotonic functions
We derive a simple criterion that ensures uniqueness, Lipschitz stabilit...
read it
IG Farben Haus
Goethe University Frankfurt, positioned among the top international research universities, offers a wide variety of academic programmes, a diverse group of research institutes, and a focus on interdisciplinary approaches to solving complex problems. Th...