Search

Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults. We address the latter by examining fault-tolerance in semantic segmentation models. Using established hardware fault models, we evaluate existing hardening techniques both in terms of accuracy and uncertainty and introduce ReLUMax, a novel simple activation function designed to enhance resilience against transient faults. ReLUMax integrates seamlessly into existing architectures without time overhead. Our experiments demonstrate that ReLUMax effectively improves robustness, preserving performance and boosting prediction confidence, thus contributing to the development of reliable autonomous driving systems., Comment: Accepted ECCV 2024 UnCV Workshop - https://github.com/iurada/neutron-segmentation

Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression. Case studies for compression models are available at \href{https://github.com/venturusbr/cv-model-compression}{https://github.com/venturusbr/cv-model-compression}.

Predictions often influence the reality which they aim to predict, an effect known as performativity. Existing work focuses on accuracy maximization under this effect, but model deployment may have important unintended impacts, especially in multiagent scenarios. In this work, we investigate performative prediction in a concrete game-theoretic setting where social welfare is an alternative objective to accuracy maximization. We explore a collective risk dilemma scenario where maximising accuracy can negatively impact social welfare, when predicting collective behaviours. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design., Comment: Accepted to ICML 2024 Workshop on Agentic Markets, Vienna, Austria

Altruistic cooperation is costly yet socially desirable. As a result, agents struggle to learn cooperative policies through independent reinforcement learning (RL). Indirect reciprocity, where agents consider their interaction partner's reputation, has been shown to stabilise cooperation in homogeneous, idealised populations. However, more realistic settings are comprised of heterogeneous agents with different characteristics and group-based social identities. We study cooperation when agents are stratified into two such groups, and allow reputation updates and actions to depend on group information. We consider two modelling approaches: evolutionary game theory, where we comprehensively search for social norms (i.e., rules to assign reputations) leading to cooperation and fairness; and RL, where we consider how the stochastic dynamics of policy learning affects the analytically identified equilibria. We observe that a defecting majority leads the minority group to defect, but not the inverse. Moreover, changing the norms that judge in and out-group interactions can steer a system towards either fair or unfair cooperation. This is made clearer when moving beyond equilibrium analysis to independent RL agents, where convergence to fair cooperation occurs with a narrower set of norms. Our results highlight that, in heterogeneous populations with reputations, carefully defining interaction norms is fundamental to tackle both dilemmas of cooperation and of fairness., Comment: Main text (9 pages, 6 figures) and appendix (7 pages, 4 figures)

Complex adaptive systems (CASs), from ecosystems to economies, are open systems and inherently dependent on external conditions. While a system can transition from one state to another based on the magnitude of change in external conditions, the rate of change -- irrespective of magnitude -- may also lead to system state changes due to a phenomenon known as a rate-induced transition (RIT). This study presents a novel framework that captures RITs in CASs through a local model and a network extension where each node contributes to the structural adaptability of others. Our findings reveal how RITs occur at a critical environmental change rate, with lower-degree nodes tipping first due to fewer connections and reduced adaptive capacity. High-degree nodes tip later as their adaptability sources (lower-degree nodes) collapse. This pattern persists across various network structures. Our study calls for an extended perspective when managing CASs, emphasizing the need to focus not only on thresholds of external conditions but also the rate at which those conditions change, particularly in the context of the collapse of surrounding systems that contribute to the focal system's resilience. Our analytical method opens a path to designing management policies that mitigate RIT impacts and enhance resilience in ecological, social, and socioecological systems. These policies could include controlling environmental change rates, fostering system adaptability, implementing adaptive management strategies, and building capacity and knowledge exchange. Our study contributes to the understanding of RIT dynamics and informs effective management strategies for complex adaptive systems in the face of rapid environmental change., Comment: 25 pages, 4 figures, 1 box, supplementary information

Forman-Ricci curvature (FRC) is a potent and powerful tool for analysing empirical networks, as the distribution of the curvature values can identify structural information that is not readily detected by other geometrical methods. Crucially, FRC captures higher-order structural information of clique complexes of a graph or Vietoris-Rips complexes, which is not readily accessible to alternative methods. However, existing FRC platforms are prohibitively computationally expensive. Therefore, herein we develop an efficient set-theoretic formulation for computing such high-order FRC in simplicial complexes. Significantly, our set theory representation reveals previous computational bottlenecks and also accelerates the computation of FRC. Finally, We provide a pseudo-code, a software implementation coined FastForman, as well as a benchmark comparison with alternative implementations. We envisage that FastForman will be used in Topological and Geometrical Data analysis for high-dimensional complex data sets. Moreover, our development paves the way for future generalisations towards efficient computations of FRC on cell complexes.

Vaccination campaigns have saved thousands of lives, reaching the farthest places in the world. These campaigns have required substantial investments and accurate coordination between several actors within the vaccine supply chain. Despite these successful strategies, the outbreak of COVID-19 has altered the objectives and rules of undertaking vaccine campaigns. Then, it is essential to consider two new facts in planning vaccination campaigns. First, some groups of infected people by the virus are more vulnerable to severe illness. Second, the virus is exceptionally contagious; sometimes, no symptoms are apparent. Accordingly, we propose a bi-objective optimization model that allows healthcare decision-makers to design effective vaccination campaigns by considering these COVID-19 characteristics and controlling the associated costs. Careful utilization of temporary and traditional vaccination centers is crucial to creating a more robust strategy. Located in suitable places, temporary centers help increase the probability of reaching groups difficult to be vaccinated while simultaneously avoiding crowd congestion and reducing the risk of spreading infections in dispensing vaccination centers. Experiments were conducted using data from an area in Santiago, Chile. The results show the model allows us to manage the resources by providing a variety of vaccination plans according to the prioritization level of each objective.

Graphics Processing Units (GPUs) are over-stressed to accelerate High-Performance Computing applications and are used to accelerate Deep Neural Networks in several domains where they have a life expectancy of many years. These conditions expose the GPUs hardware to (premature) aging, causing permanent faults to arise after the usual end-of-manufacturing test. Techniques to assess the impact of permanent faults in GPUs are then strongly required, thus allowing to estimate the reliability risk and to possibly mitigate it. In this paper, we present a method to evaluate the effects of permanent faults affecting the GPU scheduler and control units, which are the most peculiar and stressed resources, along with the first figures that allow quantifying these effects. We characterize over 5.83x10^5 permanent fault effects in the scheduler and controllers of a gate-level GPU model. Then, we map the observed error categories in software by instrumenting the code of 13 applications and two convolutional neural networks, injecting more than 1.65x10^5 permanent errors. Our two-level fault injection strategy reduces the evaluation time from hundreds of years of gate-level evaluation to hundreds of hours.We found that faults in the GPU parallelism management units can modify the opcode, the addresses, and the status of thread(s) and warp(s). The large majority (up to 99%) of these hardware permanent errors impacts the running software execution. Errors affecting the instruction operation or resource management hang the code, while 45% of errors in the parallelism management or control-flow induce silent data corruptions.

The reliability evaluation of Deep Neural Networks (DNNs) executed on Graphic Processing Units (GPUs) is a challenging problem since the hardware architecture is highly complex and the software frameworks are composed of many layers of abstraction. While software-level fault injection is a common and fast way to evaluate the reliability of complex applications, it may produce unrealistic results since it has limited access to the hardware resources and the adopted fault models may be too naive (i.e., single and double bit flip). Contrarily, physical fault injection with neutron beam provides realistic error rates but lacks fault propagation visibility. This paper proposes a characterization of the DNN fault model combining both neutron beam experiments and fault injection at software level. We exposed GPUs running General Matrix Multiplication (GEMM) and DNNs to beam neutrons to measure their error rate. On DNNs, we observe that the percentage of critical errors can be up to 61%, and show that ECC is ineffective in reducing critical errors. We then performed a complementary software-level fault injection, using fault models derived from RTL simulations. Our results show that by injecting complex fault models, the YOLOv3 misdetection rate is validated to be very close to the rate measured with beam experiments, which is 8.66x higher than the one measured with fault injection using only single-bit flips.

RISC-V architectures have gained importance in the last years due to their flexibility and open-source Instruction Set Architecture (ISA), allowing developers to efficiently adopt RISC-V processors in several domains with a reduced cost. For application domains, such as safety-critical and mission-critical, the execution must be reliable as a fault can compromise the system's ability to operate correctly. However, the application's error rate on RISC-V processors is not significantly evaluated, as it has been done for standard x86 processors. In this work, we investigate the error rate of a commercial RISC-V ASIC platform, the GAP8, exposed to a neutron beam. We show that for computing-intensive applications, such as classification Convolutional Neural Networks (CNN), the error rate can be 3.2x higher than the average error rate. Additionally, we find that the majority (96.12%) of the errors on the CNN do not generate misclassifications. Finally, we also evaluate the events that cause application interruption on GAP8 and show that the major source of incorrect interruptions is application hangs (i.g., due to an infinite loop or a racing condition).

Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving. However, recent findings indicate that transient hardware faults may corrupt the models prediction dramatically. For instance, the radiation-induced misprediction probability can be so high to impede a safe deployment of DNNs models at scale, urging the need for efficient and effective hardening solutions. In this work, we propose to tackle the reliability issue both at training and model design time. First, we show that vanilla models are highly affected by transient faults, that can induce a performances drop up to 37%. Hence, we provide three zero-overhead solutions, based on DNN re-design and re-train, that can improve DNNs reliability to transient faults up to one order of magnitude. We complement our work with extensive ablation studies to quantify the gain in performances of each hardening component., Comment: 7 pages, 6 figures

Collective risk dilemmas (CRDs) are a class of n-player games that represent societal challenges where groups need to coordinate to avoid the risk of a disastrous outcome. Multi-agent systems incurring such dilemmas face difficulties achieving cooperation and often converge to sub-optimal, risk-dominant solutions where everyone defects. In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs. We find that risk diversity places new challenges to cooperation that are not observed in homogeneous groups. We show that increasing risk diversity significantly reduces overall cooperation and hinders collective target achievement. It leads to asymmetrical changes in agents' policies -- i.e. the increase in contributions from individuals at high risk is unable to compensate for the decrease in contributions from individuals at low risk -- which overall reduces the total contributions in a population. When comparing RL behaviors to rational individualistic and social behaviors, we find that RL populations converge to fairer contributions among agents. Our results highlight the need for aligning risk perceptions among agents or develop new learning techniques that explicitly account for risk diversity., Comment: 17 pages, 24 figures. Accepted at the Cooperative AI Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

We develop a general technique of constructing new irreducible weight modules for any affine Kac-Moody algebra using the parabolic induction, in the case when the Levi factor of a parabolic subalgebra is infinite-dimensional and the central charge is nonzero. Our approach uniforms and generalizes all previously known results with imposed restrictions on inducing modules. We also define generalized Imaginary Wakimoto modules which provide an explicit realization for generic generalized Imaginary Verma modules., Comment: 20 pages

Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be particularly useful in datasets that are not as well-prepared as those in challenges, and also under scarce annotation and/or small data. We describe basic procedures: as data preparation, optimization and transfer learning, but also recent architectural choices such as use of transformer modules, alternative convolutional layers, activation functions, wide and deep networks, as well as training procedures including as curriculum, contrastive and self-supervised learning., Comment: Extended version of SIBGRAPI 2021 Tutorial Paper

We investigate the sources of Detected Unrecoverable Errors (DUEs) in GPUs exposed to neutron beams. Illegal memory accesses and interface errors are among the more likely sources of DUEs. ECC increases the launch failure events. Our test procedure has shown that ECC can reduce the DUEs caused by Illegal Address access up to 92% for Kepler and 98% for Volta.

From social contracts to climate agreements, individuals engage in groups that must collectively reach decisions with varying levels of equality and fairness. These dilemmas also pervade Distributed Artificial Intelligence, in domains such as automated negotiation, conflict resolution or resource allocation. As evidenced by the well-known Ultimatum Game -- where a Proposer has to divide a resource with a Responder -- payoff-maximizing outcomes are frequently at odds with fairness. Eliciting equality in populations of self-regarding agents requires judicious interventions. Here we use knowledge about agents' social networks to implement fairness mechanisms, in the context of Multiplayer Ultimatum Games. We focus on network-based role assignment and show that preferentially attributing the role of Proposer to low-connected nodes increases the fairness levels in a population. We evaluate the effectiveness of low-degree Proposer assignment considering networks with different average connectivity, group sizes, and group voting rules when accepting proposals (e.g. majority or unanimity). We further show that low-degree Proposer assignment is efficient, not only optimizing fairness, but also the average payoff level in the population. Finally, we show that stricter voting rules (i.e., imposing an accepting consensus as requirement for collectives to accept a proposal) attenuates the unfairness that results from situations where high-degree nodes (hubs) are the natural candidates to play as Proposers. Our results suggest new routes to use role assignment and voting mechanisms to prevent unfair behaviors from spreading on complex networks.

The investigation of curved low-dimensional systems is a topic of great research interest. Such investigations include two-dimensional systems with cylindrical symmetry. In this work, we present a numerical study of the electronic transport properties of metallic nanotubes deviating from the cylindrical form either by having a bump or a depression, and under the influence of a magnetic field. Under these circumstances, it is found that the nanotube may be used as an energy high-pass filter for electrons. It is also shown that the device can be used to tune the angular momentum of transmitted electrons., Comment: The following article has been accepted by J. of Applied Physics