Résultats de recherche pour : Machine learning

Learning the importance of training data under concept drift

Posted by Nishant Jain, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research The constantly changing nature of the world around us poses a significant challenge for the development of AI models. Often, models are trained on longitudinal data with the hope that the training data used will accurately represent inputs the model may receive […]

Learning the importance of training data under concept drift Lire l’article »

Computer Security: TN v3.0

Computer Security: TN v3.0 Remember the good old days of the Technical Network (TN), when CERN (accelerator) control systems were easily accessible from the Campus network? Unfortunately, those control systems were (and still are today!) using devices of the “Internet of Damn Insecure Stupid Things”. External protections became necessary in 2005: enter TN v2.0. While

Computer Security: TN v3.0 Lire l’article »

Beyond the Algorithm Challenge

The NASA Earth Science Technology Office (ESTO) seeks solutions to complex Earth Science problems using transformative or unconventional computing technologies such as quantum computing, quantum machine learning, neuromorphic computing, or in-memory computing. Breakthrough computing methods show promise in overcoming processing power, efficiency, and performance limitations of conventional computing methods. Once fully harnessed, these methods could

Beyond the Algorithm Challenge Lire l’article »

L’IA détecte les biais sexistes dans les urgences

Introduction Les préjugés inconscients des médecins peuvent influencer les soins d’urgence, compromettant potentiellement la santé des patients. L’intelligence artificielle générative (IA) émerge comme un outil précieux pour identifier et atténuer ces biais sournois. Dévoiler les biais cachés Des chercheurs de l’Inserm et de l’université de Bordeaux ont utilisé une IA générative avancée formée sur les

L’IA détecte les biais sexistes dans les urgences Lire l’article »

Exphormer: Scaling transformers for graph-structured data

Posted by Ameya Velingker, Research Scientist, Google Research, and Balaji Venkatachalam, Software Engineer, Google Graphs, in which objects and their relations are represented as nodes (or vertices) and edges (or links) between pairs of nodes, are ubiquitous in computing and machine learning (ML). For example, social networks, road networks, and molecular structure and interactions are

Exphormer: Scaling transformers for graph-structured data Lire l’article »

Intervening on early readouts for mitigating spurious features and simplicity bias

Posted by Rishabh Tiwari, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research Machine learning models in the real world are often trained on limited data that may contain unintended statistical biases. For example, in the CELEBA celebrity image dataset, a disproportionate number of female celebrities have blond hair, leading to classifiers incorrectly predicting “blond”

Intervening on early readouts for mitigating spurious features and simplicity bias Lire l’article »

Retour en haut