To regulate a social system comprised of self-interested agents, economic incentives are often required to induce a desirable outcome. This incentive design problem naturally possesses a bilevel structure, in which a designer modifies the rewards of the agents with incentives while anticipating the response of the agents, who play a non-cooperative game that converges to an equilibrium. The existing bilevel optimization algorithms raise a dilemma when applied to this problem: anticipating how incentives affect the agents at equilibrium requires solving the equilibrium problem repeatedly, which is computationally inefficient; bypassing the time-consuming step of equilibrium-finding can reduce the computational cost, but may lead the designer to a sub-optimal solution. To address such a dilemma, we propose a method that tackles the designer's and agents' problems simultaneously in a single loop. Specifically, at each iteration, both the designer and the agents only move one step. Nevertheless, we allow the designer to gradually learn the overall influence of the incentives on the agents, which guarantees optimality after convergence. The convergence rate of the proposed scheme is also established for a broad class of games.

The main computational task of Scientific Machine Learning (SciML) is function regression, required both for inputs as well as outputs of a simulation. Physics-Informed Neural Networks (PINNs) and neural operators (such as DeepONet) have been very effective in solving Partial Differential Equations (PDEs), but they tax computational resources heavily and cannot be readily adopted for edge computing. Here, we address this issue by considering Spiking Neural Networks (SNNs), which have shown promise in reducing energy consumption by two orders of magnitude or more. We present a SNN-based method to perform regression, which has been a challenge due to the inherent difficulty in representing a function's input domain and continuous output values as spikes. We first propose a new method for encoding continuous values into spikes based on a triangular matrix in space and time, and demonstrate its better performance compared to the existing methods. Next, we demonstrate that using a simple SNN architecture consisting of Leaky Integrate and Fire (LIF) activation and two dense layers, we can achieve relatively accurate function regression results. Moreover, we can replace the LIF with a trained Multi-Layer Perceptron (MLP) network and obtain comparable results but three times faster. Then, we introduce the DeepONet, consisting of a branch (typically a Fully-connected Neural Network, FNN) for inputs and a trunk (also a FNN) for outputs. We can build a spiking DeepONet by either replacing the branch or the trunk by a SNN. We demonstrate this new approach for classification using the SNN in the branch, achieving results comparable to the literature. Finally, we design a spiking DeepONet for regression by replacing its trunk with a SNN, and achieve good accuracy for approximating functions as well as inferring solutions of differential equations.

3D microstructural datasets are commonly used to define the geometrical domains used in finite element modelling. This has proven a useful tool for understanding how complex material systems behave under applied stresses, temperatures and chemical conditions. However, 3D imaging of materials is challenging for a number of reasons, including limited field of view, low resolution and difficult sample preparation. Recently, a machine learning method, SliceGAN, was developed to statistically generate 3D microstructural datasets of arbitrary size using a single 2D input slice as training data. In this paper, we present the results from applying SliceGAN to 87 different microstructures, ranging from biological materials to high-strength steels. To demonstrate the accuracy of the synthetic volumes created by SliceGAN, we compare three microstructural properties between the 2D training data and 3D generations, which show good agreement. This new microstructure library both provides valuable 3D microstructures that can be used in models, and also demonstrates the broad applicability of the SliceGAN algorithm.

Explainable artificial intelligence (XAI) twin systems will be a fundamental enabler of zero-touch network and service management (ZSM) for sixth-generation (6G) wireless networks. A reliable XAI twin system for ZSM requires two composites: an extreme analytical ability for discretizing the physical behavior of the Internet of Everything (IoE) and rigorous methods for characterizing the reasoning of such behavior. In this paper, a novel neuro-symbolic explainable artificial intelligence twin framework is proposed to enable trustworthy ZSM for a wireless IoE. The physical space of the XAI twin executes a neural-network-driven multivariate regression to capture the time-dependent wireless IoE environment while determining unconscious decisions of IoE service aggregation. Subsequently, the virtual space of the XAI twin constructs a directed acyclic graph (DAG)-based Bayesian network that can infer a symbolic reasoning score over unconscious decisions through a first-order probabilistic language model. Furthermore, a Bayesian multi-arm bandits-based learning problem is proposed for reducing the gap between the expected explained score and the current obtained score of the proposed neuro-symbolic XAI twin. To address the challenges of extensible, modular, and stateless management functions in ZSM, the proposed neuro-symbolic XAI twin framework consists of two learning systems: 1) an implicit learner that acts as an unconscious learner in physical space, and 2) an explicit leaner that can exploit symbolic reasoning based on implicit learner decisions and prior evidence. Experimental results show that the proposed neuro-symbolic XAI twin can achieve around 96.26% accuracy while guaranteeing from 18% to 44% more trust score in terms of reasoning and closed-loop automation.

Created by Jamy Herrmann at ECAL, MEMOGRAM is a (non)camera that prints our images in the form of a written description, inviting users to (re)discover those moments in images. Today, for many, the memories that remain are only those of images taken with digital cameras. This project uses many different techniques since it is both tangible and digital. Both versions are made in 3D printing and then wrapped with a paper explaining the steps of use. The electronics are comprised of a thermal printer (and a paper roll) connected to a custom PCB equipped with an Arduino nano and a bluetooth UART module.

Mark Minevich is a highly regarded and trusted Digital Cognitive AI Strategist, Artificial Intelligence expert, Global Social Innovation and Technology Executive, UN Advisor, Leading Author and Columnist, Private Investor/Venture Capitalist, and the principal founder and President of Going Global Ventures. He is an award-winning technology executive and has published two books and over 40 articles on AI, Industry 4.0, IoT. Mark is newly appointed Chairman of the Executive committee of AI for Good Foundation. Mark is a Chief Digital Strategist at the International Research Centre for AI, under the auspices of UNESCO. Mark is Sr. Advisor to Boston Consulting Group Boston Consulting Group. Currently, he serves as the strategic advisor and Global ambassador to the CEO and Chairman of New York based Amelia/ IPsoft Inc. Mark collaborates and advises large global enterprises both in the US and Japan (Hitachi). Mark is Advisory Partner to Canadian Growth Investments and Business Advisor to Infosec Global.   What is the definition of leadership for you? As a leader, should one create more followers or leaders? I believe that a leader should create more leaders, not followers. A leader is someone who inspires and motivates others to achieve their goals. A leader also has […]

Since photovoltaic (PV) plants require periodic maintenance, using Unmanned Aerial Vehicles (UAV) for inspections can help reduce costs. The thermal and visual inspection of PV installations is currently based on UAV photogrammetry. A UAV equipped with a Global Positioning System (GPS) receiver is assigned a flight zone: the UAV will cover it back and forth to collect images to be later composed in an orthomosaic. The UAV typically flies at a height above the ground that is appropriate to ensure that images overlap even in the presence of GPS positioning errors. However, this approach has two limitations. Firstly, it requires to cover the whole flight zone, including "empty" areas between PV module rows. Secondly, flying high above the ground limits the resolution of the images to be later inspected. The article proposes a novel approach using an autonomous UAV equipped with an RGB and a thermal camera for PV module tracking. The UAV moves along PV module rows at a lower height than usual and inspects them back and forth in a boustrophedon way by ignoring "empty" areas with no PV modules. Experimental tests performed in simulation and an actual PV plant are reported.

Edge TPUs are a domain of accelerators for low-power, edge devices and are widely used in various Google products such as Coral and Pixel devices. In this paper, we first discuss the major microarchitectural details of Edge TPUs. Then, we extensively evaluate three classes of Edge TPUs, covering different computing ecosystems, that are either currently deployed in Google products or are the product pipeline, across 423K unique convolutional neural networks. Building upon this extensive study, we discuss critical and interpretable microarchitectural insights about the studied classes of Edge TPUs. Mainly, we discuss how Edge TPU accelerators perform across convolutional neural networks with different structures. Finally, we present our ongoing efforts in developing high-accuracy learned machine learning models to estimate the major performance metrics of accelerators such as latency and energy consumption. These learned models enable significantly faster (in the order of milliseconds) evaluations of accelerators as an alternative to time-consuming cycle-accurate simulators and establish an exciting opportunity for rapid hard-ware/software co-design.

IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed false positive rate (FPR), compared to current IceCube methods. Alternatively, the GNN offers a reduction of the FPR by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.

The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization (ERM) can be detrimental to real-world performance, as it biases policy networks towards matching only open-loop behavior, showing poor results when evaluated in closed-loop. In this work, we develop an efficient and simple-to-implement principle called Closed-loop Weighted Empirical Risk Minimization (CW-ERM), in which a closed-loop evaluation procedure is first used to identify training data samples that are important for practical driving performance and then we these samples to help debias the policy network. We evaluate CW-ERM in a challenging urban driving dataset and show that this procedure yields a significant reduction in collisions as well as other non-differentiable closed-loop metrics.