Object detection systems must reliably perceive objects of interest without being overly confident to ensure safe decision-making in dynamic environments. Filtering techniques based on out-of-distribution (OoD) detection are commonly added as an extra safeguard to filter hallucinations caused by overconfidence in novel objects. Nevertheless, evaluating YOLO-family detectors and their filters under existing OoD benchmarks often leads to unsatisfactory performance. This paper studies the underlying reasons for performance bottlenecks and proposes a methodology to improve performance fundamentally. Our first contribution is a calibration of all existing evaluation results: Although images in existing OoD benchmark datasets are claimed not to have objects within in-distribution (ID) classes (i.e., categories defined in the training dataset), around 13% of objects detected by the object detector are actually ID objects. Dually, the ID dataset containing OoD objects can also negatively impact the decision boundary of filters. These ultimately lead to a significantly imprecise performance estimation. Our second contribution is to consider the task of hallucination reduction as a joint pipeline of detectors and filters. By developing a methodology to carefully synthesize an OoD dataset that semantically resembles the objects to be detected, and using the crafted OoD dataset in the fine-tuning of YOLO detectors to suppress the objectness score, we achieve a 88% reduction in overall hallucination error with a combined fine-tuned detection and filtering system on the self-driving benchmark BDD-100K. Our code and dataset are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/dnn-safety/m-hood.

Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While traditional methods can readily achieve translational invariance, rotational invariance possesses multiple challenges and remains an active area of research. Here, we present ILPO-Net (Invariant to Local Patterns Orientation Network), a novel approach that handles arbitrarily shaped patterns with the convolutional operation inherently invariant to local spatial pattern orientations using the Wigner matrix expansions. Our architecture seamlessly integrates the new convolution operator and, when benchmarked on diverse volumetric datasets such as MedMNIST and CATH, demonstrates superior performance over the baselines with significantly reduced parameter counts - up to 1000 times fewer in the case of MedMNIST. Beyond these demonstrations, ILPO-Net's rotational invariance paves the way for other applications across multiple disciplines. Our code is publicly available at https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/ILPONet.

Analyzing volumetric data with rotational invariance or equivariance is an active topic in current research. Existing deep-learning approaches utilize either group convolutional networks limited to discrete rotations or steerable convolutional networks with constrained filter structures. This work proposes a novel equivariant neural network architecture that achieves analytical Equivariance to Local Pattern Orientation on the continuous SO(3) group while allowing unconstrained trainable filters - EquiLoPO Network. Our key innovations are a group convolutional operation leveraging irreducible representations as the Fourier basis and a local activation function in the SO(3) space that provides a well-defined mapping from input to output functions, preserving equivariance. By integrating these operations into a ResNet-style architecture, we propose a model that overcomes the limitations of prior methods. A comprehensive evaluation on diverse 3D medical imaging datasets from MedMNIST3D demonstrates the effectiveness of our approach, which consistently outperforms state of the art. This work suggests the benefits of true rotational equivariance on SO(3) and flexible unconstrained filters enabled by the local activation function, providing a flexible framework for equivariant deep learning on volumetric data with potential applications across domains. Our code is publicly available at \url{https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/ILPO/-/tree/main/EquiLoPO}.

The consortium of SPATIAL Project (Security and Privacy Accountable Technology Innovations, Algorithms, and Machine Learning) announces the official start of this joint European initiative funded by the European Commission under the Horizon 2020 Research & Innovation programme. Get to know about the project, the partners and the use cases. SPATIAL planning to participate at the IoT Week 2022. Learn more about the partners through the intereviews and get to know how SPATIAL participated at the EuCNC in Grenoble (June 2022). "Digital Services Act and Digital Markets Act set a new cornerstone for digital in Europe" article.

Researchers and advocacy organizations have a long history of using algorithms, logic, modeling and similar technologies to understand how past and current conditions impact the environment now and in the future. They also use these technologies to predict how environmental impacts -- from climate change to the resulting increase in global sea levels -- will affect the world. They've used them to study how and to what extent mitigation efforts can improve the environment. Now, many organizations outside the research and advocacy fields can -- and are -- using AI to help them in their own individual sustainability and environmental protection efforts. For starters, Schneider Electric, a multinational company specializing in digital automation and energy management, is putting its own technology to use in a new flagship building in Grenoble, France.

Are passionate about contributing to solutions that benefit science and business at the same time; Are able to communicate with university and business stakeholders; Have knowledge of several of the following techniques: mathematical programming, dynamic programming, reinforcement learning, supervised learning, simulation, business analytics, heuristics, etc.; Can code in one or more of the following programming languages: Python, Java, C, Delphi, Matlab, and R; Have, or will shortly acquire, an MSc degree in Industrial Engineering, Operations Research, Applied Mathematics, or related programme; Possess excellent communication skills and are proficient in English.

The new 19,200 square meter site brings together three areas of expertise (energy, high-performance computing (HPC) and artificial intelligence) and 1,000 Atos employees who were previously based at Grenoble and the historic site in Echirolles. With a capacity of up to 1,320 people, the new site will be able to accommodate the 250 new hires planned for 2023. With this new campus, Atos reinforces its innovation strategy as the new European R&D center will promote local excellence on a worldwide scale. Funded by the Auvergne-Rhône-Alpes Region, through the European Regional Development Fund (ERDF), and by Grenoble-Alpes Métropole, this center and its 300 employees are mainly focused on Artificial Intelligence. Atos' teams have already partnered with the MIAI@Grenoble Alpes program from the Grenoble Interdisciplinary Institute of Artificial Intelligence (3IA), which has received government support.

On March 29, 2018, during the "AI for Humanity" day, Emmanuel Macron announced the "National Strategy for Artificial Intelligence", inspired by Cedric Villani's report which called for "the awakening of France and Europe" in terms of AI. For France to have a role as a world leader in AI, this report recommended the creation of a network of Interdisciplinary Institutes of Artificial Intelligence. Four three 3IAs were finally selected and financed viaa 1.5 billion euro plan. Following an AMI launched by the French National Research Agency (ANR) in July 2018, the jury selected four 3IA institute projects from the sites of Grenoble, Nice, Paris and Toulouse and requested their labeling. Specificities that do not prevent them from operating as a network and creating excellent conditions for collaboration between public and private, academic research and innovation players of all sizes.

Juan Carlos Augusto, Philippe Lalanda, Massimo Mecella Intelligent Environments are populated with numerous devices and have multiple occupants, inherently exhibit increasingly intelligent behaviour, support consistent functionality and human-centric operation (humans, as opposed to mere users, have increased requirements from a system, including, for example, intuitive interaction, protection of privacy, fault-tolerance etc.), and provide optimized resource usage. The development of Intelligent Environments is considered the first and primary step towards the realization of the Ambient Intelligence vision and requires input from research and contributions from several scientific and engineering disciplines, including computer science, software engineering, artificial intelligence, architecture, social sciences, art and design. The series of IE conferences have been consistently creating a unique blend of researchers in these disciplines, fostering cross-disciplinary discussions, debate and collaborations.

TORONTO--Sometimes a problem can become its own solution. For CEA-Leti scientists, it means that traits of resistive-RAM (ReRAM) devices that have been previously considered as "non-ideal" may be the answer to overcoming barriers to developing ReRAM-based edge-learning systems, as outlined in a recent Nature Electronics publication titled "In-situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling." It describes how RRAM, or memristor, technology can be used to create intelligent systems that learn locally at the edge, independent of the cloud. Thomas Dalgaty, a CEA-Leti scientist at France's Université Grenoble, explained how the team were able to navigate the intrinsic non-idealities of ReRAM technology--the learning algorithms used in current ReRAM-based edge approaches cannot be reconciled with device programming randomness, or variability, among others. In a telephone interview with EE Times, he said the solution was to implement a Markov Chain Monte Carlo (MCMC) sampling learning algorithm in a fabricated chip that acts as a Bayesian machine-learning model, which actively exploited memristor randomness. For the purposes of the research, Dalgaty said it's important to clearly define what is meant by an edge system.