For many applications in image analysis, learning models that are invariant to translations and rotations is paramount. This is the case, for example, in medical imaging where the objects of interest can appear at arbitrary positions, with arbitrary orientations. As of today, Convolutional Neural Networks (CNN) are one of the most powerful tools for image analysis. They achieve, thanks to convolutions, an invariance with respect to translations. In this work, we present a new type of convolutional layer that takes advantage of Bessel functions, well known in physics, to build Bessel-CNNs (B-CNNs) that are invariant to all the continuous set of possible rotation angles by design.

Motor prostheses aim to restore function to disabled patients. Despite compelling proof of concept systems, barriers to clinical translation remain. One challenge is to develop a low-power, fully-implantable system that dissipates only minimal power so as not to damage tissue. To this end, we implemented a Kalman-filter based decoder via a spiking neural network (SNN) and tested it in brain-machine interface (BMI) experiments with a rhesus monkey. The Kalman filter was trained to predict the arm's velocity and mapped on to the SNN using the Neural Engineering Framework (NEF). A 2,000-neuron embedded Matlab SNN implementation runs in real-time and its closed-loop performance is quite comparable to that of the standard Kalman filter. The success of this closed-loop decoder holds promise for hardware SNN implementations of statistical signal processing algorithms on neuromorphic chips, which may offer power savings necessary to overcome a major obstacle to the successful clinical translation of neural motor prostheses. Present: Research Fellow F.R.S.-FNRS, Systmod Unit, University of Liege, Belgium.

Supervised deep learning was recently introduced in high-contrast imaging (HCI) through the SODINN algorithm, a convolutional neural network designed for exoplanet detection in angular differential imaging (ADI) datasets. The benchmarking of HCI algorithms within the Exoplanet Imaging Data Challenge (EIDC) showed that (i) SODINN can produce a high number of false positives in the final detection maps, and (ii) algorithms processing images in a more local manner perform better. This work aims to improve the SODINN detection performance by introducing new local processing approaches and adapting its learning process accordingly. We propose NA-SODINN, a new deep learning binary classifier based on a convolutional neural network (CNN) that better captures image noise correlations in ADI-processed frames by identifying noise regimes. Our new approach was tested against its predecessor, as well as two SODINN-based hybrid models and a more standard annular-PCA approach, through local receiving operating characteristics (ROC) analysis of ADI sequences from the VLT/SPHERE and Keck/NIRC-2 instruments. Results show that NA-SODINN enhances SODINN in both sensitivity and specificity, especially in the speckle-dominated noise regime. NA-SODINN is also benchmarked against the complete set of submitted detection algorithms in EIDC, in which we show that its final detection score matches or outperforms the most powerful detection algorithms.Throughout the supervised machine learning case, this study illustrates and reinforces the importance of adapting the task of detection to the local content of processed images.

Metasurfaces offer a flexible framework for the manipulation of light properties in the realm of thin film optics. Specifically, the polarization of light can be effectively controlled through the use of thin phase plates. This study aims to introduce a surrogate optimization framework for these devices. The framework is applied to develop two kinds of vortex phase masks (VPMs) tailored for application in astronomical high-contrast imaging. Computational intelligence techniques are exploited to optimize the geometric features of these devices. The large design space and computational limitations necessitate the use of surrogate models like partial least squares Kriging, radial basis functions, or neural networks. However, we demonstrate the inadequacy of these methods in modeling the performance of VPMs. To address the shortcomings of these methods, a data-efficient evolutionary optimization setup using a deep neural network as a highly accurate and efficient surrogate model is proposed. The optimization process in this study employs a robust particle swarm evolutionary optimization scheme, which operates on explicit geometric parameters of the photonic device. Through this approach, optimal designs are developed for two design candidates. In the most complex case, evolutionary optimization enables optimization of the design that would otherwise be impractical (requiring too much simulations). In both cases, the surrogate model improves the reliability and efficiency of the procedure, effectively reducing the required number of simulations by up to 75% compared to conventional optimization techniques.

EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the predictions of an Artificial Intelligence (AI) system. Many XAI approaches have emerged in recent years. Consequently, a subfield related to the evaluation of XAI methods has gained considerable attention, with the aim to determine which methods provide the best explanation using various approaches and criteria. However, the literature lacks a comparison of the evaluation metrics themselves, that one can use to evaluate XAI methods. This work aims to fill this gap by comparing 14 different metrics when applied to nine state-of-the-art XAI methods and three dummy methods (e.g., random saliency maps) used as references. Experimental results show which of these metrics produces highly correlated results, indicating potential redundancy. We also demonstrate the significant impact of varying the baseline hyperparameter on the evaluation metric values. Finally, we use dummy methods to assess the reliability of metrics in terms of ranking, pointing out their limitations.

Summary: A new deep learning algorithm is able to quantify arousal and awareness in humans at the same time. New research supported by the EU-funded HBP SGA3 and DoCMA projects is giving scientists new insight into human consciousness. Led by Korea University and projects' partner University of Liège (Belgium), the research team has developed an explainable consciousness indicator (ECI) to explore different components of consciousness. Their findings were published in the journal Nature Communications. Consciousness can be described as having two components: arousal (i.e.

One night in October, 2009, a young man lay in an fMRI scanner in Liège, Belgium. Five years earlier, he'd suffered a head trauma in a motorcycle accident, and since then he hadn't spoken. He was said to be in a "vegetative state." A neuroscientist named Martin Monti sat in the next room, along with a few other researchers. For years, Monti and his postdoctoral adviser, Adrian Owen, had been studying vegetative patients, and they had developed two controversial hypotheses.

In a recently published paper, a pair of academics propose that the application of artificial intelligence can offer a potent weapon against antitrust behavior in the Big Tech sector. This is the very industry that has advanced this technology, noted one of those academics, Giovana Massarotto, a Center for Technology, Innovation and Competition academic fellow at the University of Pennsylvania Carey Law School and an adjunct professor at the University of Iowa. She underscored this fact in an article for Bloomberg Law, in which she maintains that "the present economic democracy propaganda against Big Tech is not the solution to increase competition in fast-moving technology markets." In fact, she says, the industry's ingenuity is needed to achieve our nation's pro-competition goals. Massarotto and University of Liege (Belgium) Associate Professor Ashwin Ittoo write about their "antitrust machine learning application" (AML) which shows the potential for AI to "assist antitrust agencies in detecting anticompetitive practices faster."

In a recently published paper, a pair of academics propose that the application of artificial intelligence can offer a potent weapon against antitrust behavior in the Big Tech sector. This is the very industry that has advanced this technology, noted one of those academics, Giovana Massarotto, a Center for Technology, Innovation and Competition academic fellow at the University of Pennsylvania Carey Law School and an adjunct professor at the University of Iowa. She underscored this fact in an article for Bloomberg Law, in which she maintains that "the present economic democracy propaganda against Big Tech is not the solution to increase competition in fast-moving technology markets." In fact, she says, the industry's ingenuity is needed to achieve our nation's pro-competition goals. Massarotto and University of Liege (Belgium) Associate Professor Ashwin Ittoo write about their "antitrust machine learning application" (AML) which shows the potential for AI to "assist antitrust agencies in detecting anticompetitive practices faster."

This entry is a part of the NYU Center for Data Science blog's recurring guest editorial series. Irina Espejo Morales is a CDS Ph.D. student in data science and also a DeepMind fellow. Kyle Cranmer is a CDS professor of data science and professor of physics at the NYU College of Arts & Science. Lukas Heinrich is a staff scientist at CERN working with the ATLAS experiment at the LHC and former NYU graduate student. Gilles Louppe is an associate professor in artificial intelligence and deep learning at the University of Liège (Belgium) and former Moore Sloan fellow.