Related papers: Compositional Falsification of Cyber-Physical Syst…
Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we…
Autonomous systems embedded with machine learning modules often rely on deep neural networks for classifying different objects of interest in the environment or different actions or strategies to take for the system. Due to the…
Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply…
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has transferred some prior knowledge about compositionality to…
Many of today's machine learning (ML) systems are not built from scratch, but are compositions of an array of {\em modular learning components} (MLCs). The increasing use of MLCs significantly simplifies the ML system development cycles.…
In this thesis a comprehensive verification framework is proposed to contend with some important issues in composability verification and a verification process is suggested to verify composability of different kinds of systems models, such…
Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract…
This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. Momentum PL (MPL) trains a connectionist temporal…
Mechanized verification of liveness properties for infinite programs with effects and nondeterminism is challenging. Existing temporal reasoning frameworks operate at the level of models such as traces and automata. Reasoning happens at a…
Cyber Physical Systems (CPSs) are often black box systems for which no exact model exists. Automata learning allows to build abstract models of CPSs and is used in several scenarios, i.e. simulation, monitoring, and test case generation.…
A formal description of a Cyber-Physical system should include a rigorous specification of the computational and physical components involved, as well as their interaction. Such a description, thus, lends itself to a compositional model…
The behavior of a cyber-physical system (CPS) is usually defined in terms of the input and output signals processed by sensors and actuators. Requirements specifications of CPSs are typically expressed using signal-based temporal…
In this paper, we focus on the problem of compositional synthesis of controllers enforcing signal temporal logic (STL) tasks over a class of continuous-time nonlinear interconnected systems. By leveraging the idea of funnel-based control,…
Modern cyber-physical systems (CPS) can consist of various networked components and agents interacting and communicating with each other. In the context of spatially distributed CPS, these connections can be dynamically dependent on the…
Class-conditional noise commonly exists in machine learning tasks, where the class label is corrupted with a probability depending on its ground-truth. Many research efforts have been made to improve the model robustness against the…
We propose and demonstrate a compositional framework for training and verifying reinforcement learning (RL) systems within a multifidelity sim-to-real pipeline, in order to deploy reliable and adaptable RL policies on physical hardware. By…
We consider learning and compositionality as the key mechanisms towards simulating human-like intelligence. While each mechanism is successfully achieved by neural networks and symbolic AIs, respectively, it is the combination of the two…
The use of machine learning interatomic potentials (MLIPs) in simulations of materials is a state-of-the-art approach, which allows achieving nearly \textit{ab initio} accuracy with orders of magnitude less computational cost.…
We introduce a transition system based specification of cyber-physical systems whose semantics is compositional with respect to a family of algebraic products. We give sufficient conditions for execution of a product to be correctly…
Cyber-physical systems (CPS) are assemblies of networked, heterogeneous, hardware, and software components sensing, evaluating, and actuating a physical environment. This heterogeneity induces complexity that makes CPSs challenging to model…