fortiss

∙ München , Germany ∙ 0 followers

fortiss is an institute at the Technical University of Munich, a university but legally independent, non-commercial research institution in the legal form of a non-profit limited liability company.

Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks

Training deep neural networks for solving machine learning problems is o...
11/17/2016 ∙ by Hao Shen, et al. ∙ 0 ∙ share

read it
Maximum Resilience of Artificial Neural Networks

The deployment of Artificial Neural Networks (ANNs) in safety-critical a...
04/28/2017 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Verification of Binarized Neural Networks

We study the problem of formal verification of Binarized Neural Networks...
10/09/2017 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Verification of Binarized Neural Networks via Inter-Neuron Factoring

We study the problem of formal verification of Binarized Neural Networks...
10/09/2017 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Quantitative Projection Coverage for Testing ML-enabled Autonomous Systems

Systematically testing models learned from neural networks remains a cru...
05/11/2018 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Towards Dependability Metrics for Neural Networks

Neural networks and other data engineered models are instrumental in dev...
06/06/2018 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
ML + FV = ? A Survey on the Application of Machine Learning to Formal Verification

Formal Verification (FV) and Machine Learning (ML) can seem incompatible...
06/10/2018 ∙ by Moussa Amrani, et al. ∙ 0 ∙ share

read it
Runtime Monitoring Neural Activation Patterns

For using neural networks in safety critical domains, it is important to...
09/18/2018 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Runtime Monitoring Neuron Activation Patterns

For using neural networks in safety critical domains, it is important to...
09/18/2018 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Compliance in Real Time Multiset Rewriting Models

The notion of compliance in Multiset Rewriting Models (MSR) has been int...
11/12/2018 ∙ by Max Kanovich, et al. ∙ 0 ∙ share

read it
A Differential Topological View of Challenges in Learning with Feedforward Neural Networks

Among many unsolved puzzles in theories of Deep Neural Networks (DNNs), ...
11/26/2018 ∙ by Hao Shen, et al. ∙ 0 ∙ share

read it
Traceability of Deep Neural Networks

[Context.] The success of deep learning makes its usage more and more te...
12/17/2018 ∙ by Vincent Aravantinos, et al. ∙ 0 ∙ share

read it
Architecting Dependable Learning-enabled Autonomous Systems: A Survey

We provide a summary over architectural approaches that can be used to c...
02/27/2019 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
A Generative Map for Image-based Camera Localization

In image-based camera localization systems, information about the enviro...
02/18/2019 ∙ by Mingpan Guo, et al. ∙ 0 ∙ share

read it
Towards Safety Verification of Direct Perception Neural Networks

We study the problem of safety verification of direct perception neural ...
04/09/2019 ∙ by Chih-Hong Cheng, et al. ∙ 0 ∙ share

read it
Generating Requirements Out of Thin Air: Towards Automated Feature Identification for New Apps

App store mining has proven to be a promising technique for requirements...
09/25/2019 ∙ by Tahira Iqbal, et al. ∙ 0 ∙ share

read it
Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization

Many current behavior generation methods struggle to handle real-world t...
03/06/2020 ∙ by Patrick Hart, et al. ∙ 0 ∙ share

read it
Robust Stochastic Bayesian Games for Behavior Space Coverage

A key challenge in multi-agent systems is the design of intelligent agen...
03/25/2020 ∙ by Julian Bernhard, et al. ∙ 0 ∙ share

read it
Leveraging Context-awareness to Better Support the IoT Cloud-Edge Continuum

Novel Internet of Things (IoT) requirements derived from a broader inter...
04/30/2020 ∙ by Liliana I. Carvalho, et al. ∙ 0 ∙ share

read it
A Cloud-Based Collaboration Platform for Model-Based Design of Cyber-Physical Systems

Businesses, particularly small and medium-sized enterprises, aiming to s...
05/05/2020 ∙ by Peter Gorm Larsen, et al. ∙ 0 ∙ share

read it
toki: A Build- and Test-Platform for Prototyping and Evaluating Operating System Concepts in Real-Time Environments

Typically, even low-level operating system concepts, such as resource sh...
09/01/2020 ∙ by Oliver Horst, et al. ∙ 0 ∙ share

read it

fortiss

Featured Researchers

Hao Shen

Chih-Hong Cheng

Vincent Aravantinos

Harald Ruess

Vivek Nigam

Thomas Brunner

Chung-Hao Huang

Tahira Iqbal

Julian Bernhard

Dhiraj Gulati

Stefan Matthes

Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks

Maximum Resilience of Artificial Neural Networks

Verification of Binarized Neural Networks

Verification of Binarized Neural Networks via Inter-Neuron Factoring

Quantitative Projection Coverage for Testing ML-enabled Autonomous Systems

Towards Dependability Metrics for Neural Networks

ML + FV = ? A Survey on the Application of Machine Learning to Formal Verification

Runtime Monitoring Neural Activation Patterns

Runtime Monitoring Neuron Activation Patterns

Compliance in Real Time Multiset Rewriting Models

A Differential Topological View of Challenges in Learning with Feedforward Neural Networks

Traceability of Deep Neural Networks

Architecting Dependable Learning-enabled Autonomous Systems: A Survey

A Generative Map for Image-based Camera Localization

Towards Safety Verification of Direct Perception Neural Networks

Generating Requirements Out of Thin Air: Towards Automated Feature Identification for New Apps

Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization

Robust Stochastic Bayesian Games for Behavior Space Coverage

Leveraging Context-awareness to Better Support the IoT Cloud-Edge Continuum

A Cloud-Based Collaboration Platform for Model-Based Design of Cyber-Physical Systems

toki: A Build- and Test-Platform for Prototyping and Evaluating Operating System Concepts in Real-Time Environments