arXiv research

Bayesian reflex models AI learning like the autonomic nervous system.

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. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…

A central goal of neuroscience is to understand how activity in the nervous system is related to features of the external world, or to features of the nervous system itself. A common approach is to model neural responses as a weighted combination of external features, or vice versa. The structure of the model weights c…

This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.

Generalizes energy-momentum method for non-autonomous Hamiltonian systems.

PhysioMTL learns personalized HRV rhythms from wearable data, improving prediction and counterfactual analysis.

Proves rigidity of 3D partially hyperbolic systems via autonomous dynamics.

The study explores autonomous systems and their connections to contact geometry and Frobenius manifolds.

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. This feature is inspired by the communication principles in the nervous system of small …

The study improves deep learning models for safer autonomous vehicles.

This work improves safety validation of autonomous vehicles by finding interpretable failures.

Bayesian inference models failure distributions in autonomous systems.

In this work we investigate intra-day patterns of activity on a population of 7,261 users of mobile health wearable devices and apps. We show that: (1) using intra-day step and sleep data recorded from passive trackers significantly improves classification performance on self-reported chronic conditions related to ment…

Develops a method to simulate rare dangerous events in autonomous systems.

Graph Attention Networks predict disease state from single-cell data.

Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks…

The paper extends conformal prediction to MDP trajectories for autonomous systems.

This paper presents a novel approach for automatic rule learning applicable to an autonomous driving system using real driving data.

The Surprise index assesses autonomous systems' competency in uncertain environments.

End-to-end autonomous driving perception learns latent features for better performance.

New model enables AI to learn autonomously.

Study learns dynamics of linear systems from multiple short trajectories.

Let $dx_i/dt=f_i(x_1,\cdots,x_n)$, ($i=1,\cdots,n$) be a system of $n$ first order autonomous ordinary differential equations. We use E. Cartan's equivalence method to study the invariants of this system under diffeomorphisms of the form $Φ(t,x_1,\cdots,x_n)=(\varphi_0(t),\varphi_1(x_1),\cdots,\varphi_1(x_1))$.

Studies geometric mechanics for autonomous and nonautonomous systems.

Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications:…

Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo. It has been successfully deployed in commercial vehicles like Mobileye's path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthe…

Volumetric analysis of brain ventricle (BV) structure is a key tool in the study of central nervous system development in embryonic mice. High-frequency ultrasound (HFU) is the only non-invasive, real-time modality available for rapid volumetric imaging of embryos in utero. However, manual segmentation of the BV from H…

We develop a new method to estimate failure probabilities in complex systems.

Bayesian optimization identifies optimal alloy formulations.

A method uses non-autonomous equations to classify time signals efficiently.

This paper improves parameter estimation for autonomous systems with unmodeled dynamics.

Study connects symmetries in dynamical systems to phase plane representations.

Future autonomous systems need reliable world models and complex action sequences.

Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot learning is proposed, with the aim of bypassing the manual annotation step requ…

Multiple Sclerosis is a degenerative condition of the central nervous system that affects nearly 2.5 million of individuals in terms of their physical, cognitive, psychological and social capabilities. Researchers are currently investigating on the use of patient reported outcome measures for the assessment of impact a…

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). SIM-CE contains an implementation of the mathematical models of C. elegans's neurons and synapses, in Simulink, whi…

Proposes an autonomous IDS using multiple learning techniques.

Study identifies and validates a method for system identification of Markov jump linear systems.

BagCert efficiently certifies robustness against adversarial patches on image classifiers.

VerifAI toolkit improves neural network-based aircraft taxiing system safety.

Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real-world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation-driven methods such as Adaptive Stress Testing (AST) have b…

A Lie system is the non-autonomous system of differential equations describing the integral curves of a non-autonomous vector field taking values in a finite-dimensional Lie algebra of vector fields, a so-called Vessiot--Guldberg Lie algebra. This work pioneers the analysis of Lie systems admitting a Vessiot--Guldberg …

While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing. Real-world testing, the $\textit{de facto}$ evaluation environment, places the public in danger, and, due to the rare nature of accidents, will require billions of miles in or…

While machine learning systems show high success rate in many complex tasks, research shows they can also fail in very unexpected situations. Rise of machine learning products in safety-critical industries cause an increase in attention in evaluating model robustness and estimating failure probability in machine learni…

This work develops agents to learn generalizable policies for dynamic network environments.

Reduces multisymplectic Lie systems through symmetry analysis.

Robot science discovers new materials faster.

Proposes a method to improve pWCET estimation for heavy-tailed distributions.