Search Results for author: Radu Grosu

Found 51 papers, 16 papers with code

The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits

no code implementations ICML 2020 Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks.

reinforcement-learning Reinforcement Learning (RL)

Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving

1 code implementation26 Mar 2024 Axel Brunnbauer, Luigi Berducci, Peter Priller, Dejan Nickovic, Radu Grosu

Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies.

Autonomous Driving

Gated Chemical Units

no code implementations30 Jan 2024 Mónika Farsang, Radu Grosu

By observing that the TG corresponds to the forget gate (FG) in traditional gated recurrent units, we provide a new formulation of these units as neural ODEs.

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels

no code implementations25 Jan 2024 Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable scalability and accuracy margin.

Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields

no code implementations18 Jan 2024 Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observed in the mammalian retina.

Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?

no code implementations21 Nov 2023 Mónika Farsang, Mathias Lechner, David Lung, Ramin Hasani, Daniela Rus, Radu Grosu

In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks.

Autonomous Driving

Real-Time Recurrent Reinforcement Learning

no code implementations8 Nov 2023 Julian Lemmel, Radu Grosu

In this paper we propose real-time recurrent reinforcement learning (RTRRL), a biologically plausible approach to solving discrete and continuous control tasks in partially-observable markov decision processes (POMDPs).

Continuous Control reinforcement-learning

Learning Adaptive Safety for Multi-Agent Systems

1 code implementation19 Sep 2023 Luigi Berducci, Shuo Yang, Rahul Mangharam, Radu Grosu

Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents.

Enhancing Robot Learning through Learned Human-Attention Feature Maps

1 code implementation29 Aug 2023 Daniel Scheuchenstuhl, Stefan Ulmer, Felix Resch, Luigi Berducci, Radu Grosu

In this paper, we propose a novel approach to model and emulate the human attention with an approximate prediction model.

Imitation Learning object-detection +2

Robustness Analysis of Continuous-Depth Models with Lagrangian Techniques

no code implementations23 Aug 2023 Sophie A. Neubauer, Radu Grosu

To this end, we review LRT-NG, SLR, and GoTube, algorithms for constructing a tight reachtube, that is, an over-approximation of the set of states reachable within a given time-horizon, and provide guarantees for the reachtube bounds.

On the Benefits of Biophysical Synapses

no code implementations8 Mar 2023 Julian Lemmel, Radu Grosu

First, they allow to pack more parameters for a given number of neurons and synapses.

Time Series Time Series Prediction

IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels

1 code implementation28 Oct 2022 Shrajan Bhandary, Zahra Babaiee, Dejan Kostyszyn, Tobias Fechter, Constantinos Zamboglou, Anca-Ligia Grosu, Radu Grosu

Despite the success of convolutional neural networks for 3D medical-image segmentation, the architectures currently used are still not robust enough to the protocols of different scanners, and the variety of image properties they produce.

Image Segmentation Inductive Bias +2

Pruning by Active Attention Manipulation

no code implementations20 Oct 2022 Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu

On CIFAR-10 dataset, without requiring a pre-trained baseline network, we obtain 1. 02% and 1. 19% accuracy gain and 52. 3% and 54% parameters reduction, on ResNet56 and ResNet110, respectively.

Safe Policy Improvement in Constrained Markov Decision Processes

no code implementations20 Oct 2022 Luigi Berducci, Radu Grosu

The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the construction of a reward signal and consists of the iterative application of many policy-improvement steps.

Reinforcement Learning (RL)

Entangled Residual Mappings

no code implementations2 Jun 2022 Mathias Lechner, Ramin Hasani, Zahra Babaiee, Radu Grosu, Daniela Rus, Thomas A. Henzinger, Sepp Hochreiter

Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers.

Inductive Bias Representation Learning

End-to-End Sensitivity-Based Filter Pruning

no code implementations15 Apr 2022 Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu

Moreover, by training the pruning scores of all layers simultaneously our method can account for layer interdependencies, which is essential to find a performant sparse sub-network.

3D-OOCS: Learning Prostate Segmentation with Inductive Bias

1 code implementation29 Oct 2021 Shrajan Bhandary, Zahra Babaiee, Dejan Kostyszyn, Tobias Fechter, Constantinos Zamboglou, Anca-Ligia Grosu, Radu Grosu

Despite the great success of convolutional neural networks (CNN) in 3D medical image segmentation tasks, the methods currently in use are still not robust enough to the different protocols utilized by different scanners, and to the variety of image properties or artefacts they produce.

Edge Detection Image Segmentation +4

Hierarchical Potential-based Reward Shaping from Task Specifications

1 code implementation6 Oct 2021 Luigi Berducci, Edgar A. Aguilar, Dejan Ničković, Radu Grosu

The automatic synthesis of policies for robotic-control tasks through reinforcement learning relies on a reward signal that simultaneously captures many possibly conflicting requirements.

Autonomous Driving Reinforcement Learning (RL)

DeepSTL -- From English Requirements to Signal Temporal Logic

no code implementations21 Sep 2021 Jie He, Ezio Bartocci, Dejan Ničković, Haris Isakovic, Radu Grosu

In this paper we propose DeepSTL, a tool and technique for the translation of informal requirements, given as free English sentences, into Signal Temporal Logic (STL), a formal specification language for cyber-physical systems, used both by academia and advanced research labs in industry.

Translation

GoTube: Scalable Stochastic Verification of Continuous-Depth Models

1 code implementation18 Jul 2021 Sophie Gruenbacher, Mathias Lechner, Ramin Hasani, Daniela Rus, Thomas A. Henzinger, Scott Smolka, Radu Grosu

Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states.

Adversarial Training is Not Ready for Robot Learning

no code implementations15 Mar 2021 Mathias Lechner, Ramin Hasani, Radu Grosu, Daniela Rus, Thomas A. Henzinger

Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop.

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

1 code implementation8 Mar 2021 Axel Brunnbauer, Luigi Berducci, Andreas Brandstätter, Mathias Lechner, Ramin Hasani, Daniela Rus, Radu Grosu

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms.

Continuous Control Reinforcement Learning (RL)

On The Verification of Neural ODEs with Stochastic Guarantees

no code implementations16 Dec 2020 Sophie Gruenbacher, Ramin Hasani, Mathias Lechner, Jacek Cyranka, Scott A. Smolka, Radu Grosu

We show that Neural ODEs, an emerging class of time-continuous neural networks, can be verified by solving a set of global-optimization problems.

Lagrangian Reachtubes: The Next Generation

1 code implementation14 Dec 2020 Sophie Gruenbacher, Jacek Cyranka, Mathias Lechner, Md. Ariful Islam, Scott A. Smolka, Radu Grosu

Secondly, it computes the next reachset as the intersection of two balls: one based on the Cartesian metric and the other on the new metric.

ResNets, NeuralODEs and CT-RNNs are Particular Neural Regulatory Networks

no code implementations26 Feb 2020 Radu Grosu

This paper shows that ResNets, NeuralODEs, and CT-RNNs, are particular neural regulatory networks (NRNs), a biophysical model for the nonspiking neurons encountered in small species, such as the C. elegans nematode, and in the retina of large species.

A Nonparametric Bayesian Model for Sparse Dynamic Multigraphs

no code implementations11 Oct 2019 Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham W. Taylor, Sinead A. Williamson

As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure that underpins these interactions.

Clustering

Neural Simplex Architecture

no code implementations1 Aug 2019 Dung T. Phan, Radu Grosu, Nils Jansen, Nicola Paoletti, Scott A. Smolka, Scott D. Stoller

NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance.

Continuous Control

Sequential Edge Clustering in Temporal Multigraphs

no code implementations28 May 2019 Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham W. Taylor, Sinead A. Williamson

Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner.

Clustering

Liquid Time-constant Recurrent Neural Networks as Universal Approximators

no code implementations1 Nov 2018 Ramin M. Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

In this paper, we introduce the notion of liquid time-constant (LTC) recurrent neural networks (RNN)s, a subclass of continuous-time RNNs, with varying neuronal time-constant realized by their nonlinear synaptic transmission model.

A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems

no code implementations16 Oct 2018 Denise Ratasich, Faiq Khalid, Florian Geissler, Radu Grosu, Muhammad Shafique, Ezio Bartocci

Furthermore, this paper presents the main challenges in building a resilient IoT for CPS which is crucial in the era of smart CPS with enhanced connectivity (an excellent example of such a system is connected autonomous vehicles).

Anomaly Detection Autonomous Vehicles

Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?

1 code implementation11 Sep 2018 Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as the model of biological neural circuits reparameterized for the control of an alternative task.

Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks

no code implementations11 Sep 2018 Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus

In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level.

Neural State Classification for Hybrid Systems

1 code implementation26 Jul 2018 Dung Phan, Nicola Paoletti, Timothy Zhang, Radu Grosu, Scott A. Smolka, Scott D. Stoller

We introduce the State Classification Problem (SCP) for hybrid systems, and present Neural State Classification (NSC) as an efficient solution technique.

Classification General Classification

Dynamic Network Model from Partial Observations

no code implementations NeurIPS 2018 Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec

We propose a novel framework for providing a non-parametric dynamic network model--based on a mixture of coupled hierarchical Dirichlet processes-- based on data capturing cascade node infection times.

Open-Ended Question Answering

Neuronal Circuit Policies

1 code implementation22 Mar 2018 Mathias Lechner, Ramin M. Hasani, Radu Grosu

We propose an effective way to create interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds.

Reinforcement Learning (RL)

How to Learn a Model Checker

no code implementations5 Dec 2017 Dung Phan, Radu Grosu, Nicola Paoletti, Scott A. Smolka, Scott D. Stoller

We show how machine-learning techniques, particularly neural networks, offer a very effective and highly efficient solution to the approximate model-checking problem for continuous and hybrid systems, a solution where the general-purpose model checker is replaced by a model-specific classifier trained by sampling model trajectories.

BIG-bench Machine Learning

Worm-level Control through Search-based Reinforcement Learning

no code implementations9 Nov 2017 Mathias Lechner, Radu Grosu, Ramin M. Hasani

We model the tap-withdrawal (TW) neural circuit of the nematode, \textit{C. elegans}, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neural parameters as a policy for controlling the inverted pendulum problem.

reinforcement-learning Reinforcement Learning (RL)

A Component-Based Simplex Architecture for High-Assurance Cyber-Physical Systems

1 code implementation16 Apr 2017 Dung Phan, Junxing Yang, Matthew Clark, Radu Grosu, John D. Schierman, Scott A. Smolka, Scott D. Stoller

We present Component-Based Simplex Architecture (CBSA), a new framework for assuring the runtime safety of component-based cyber-physical systems (CPSs).

Systems and Control

Non-Associative Learning Representation in the Nervous System of the Nematode Caenorhabditis elegans

no code implementations18 Mar 2017 Ramin M. Hasani, Magdalena Fuchs, Victoria Beneder, Radu Grosu

Caenorhabditis elegans (C. elegans) illustrated remarkable behavioral plasticities including complex non-associative and associative learning representations.

SIM-CE: An Advanced Simulink Platform for Studying the Brain of Caenorhabditis elegans

no code implementations18 Mar 2017 Ramin M. Hasani, Victoria Beneder, Magdalena Fuchs, David Lung, Radu Grosu

We introduce SIM-CE, an advanced, user-friendly modeling and simulation environment in Simulink for performing multi-scale behavioral analysis of the nervous system of Caenorhabditis elegans (C. elegans).

An Automated Auto-encoder Correlation-based Health-Monitoring and Prognostic Method for Machine Bearings

no code implementations18 Mar 2017 Ramin M. Hasani, Guodong Wang, Radu Grosu

We demonstrate the superiority of the AEC over many other state-of-the-art approaches for the health monitoring and prognostic of machine bearings.

Attribute

ARES: Adaptive Receding-Horizon Synthesis of Optimal Plans

no code implementations21 Dec 2016 Anna Lukina, Lukas Esterle, Christian Hirsch, Ezio Bartocci, Junxing Yang, Ashish Tiwari, Scott A. Smolka, Radu Grosu

Inspired by Importance Splitting, the length of the horizon and the number of particles are chosen such that at least one particle reaches a next-level state, that is, a state where the cost decreases by a required delta from the previous-level state.

Extracting Implicit Social Relation for Social Recommendation Techniques in User Rating Prediction

no code implementations5 Dec 2016 Seyed Mohammad Taheri, Hamidreza Mahyar, Mohammad Firouzi, Elahe Ghalebi K., Radu Grosu, Ali Movaghar

Hence, we build our method, called Hell-TrustSVD, on top of the state-of-the-art social recommendation technique to incorporate both the extracted implicit social relations and ratings given by users on the prediction of items for an active user.

Recommendation Systems Relation +1

Temporal Logic as Filtering

1 code implementation27 Oct 2015 Alena Rodionova, Ezio Bartocci, Dejan Nickovic, Radu Grosu

We also provide a quantitative semantics for MTL, which measures the normalized, maximum number of times a formula is satisfied within its associated kernel, by a given signal.

Logic in Computer Science 03B44 F.4.1; D.3.1

Deep Neural Programs for Adaptive Control in Cyber-Physical Systems

no code implementations13 Feb 2015 Konstantin Selyunin, Denise Ratasich, Ezio Bartocci, Radu Grosu

We introduce Deep Neural Programs (DNP), a novel programming paradigm for writing adaptive controllers for cy-ber-physical systems (CPS).

Monitoring with uncertainty

no code implementations24 Aug 2013 Ezio Bartocci, Radu Grosu

We discuss the problem of runtime verification of an instrumented program that misses to emit and to monitor some events.

Cannot find the paper you are looking for? You can Submit a new open access paper.