Artificial Intelligence for the Assessment of Peritoneal Carcinosis during Diagnostic Laparoscopy for Advanced Ovarian Cancer

A new framework named TrajSyn has been introduced to facilitate privacy-preserving dataset distillation from federated model trajectories, enabling effective server-side adversarial training without accessing raw client data. This innovation addresses the challenges posed by adversarial perturbations in deep learning models deployed on edge devices, particularly in Federated Learning settings where data privacy is paramount.

A review of machine learning applications in archaeology reveals a significant increase in the use of artificial intelligence (AI) across various archaeological subfields from 1997 to 2022, particularly after 2019. The study analyzed 135 articles, highlighting tasks such as automatic structure detection and artifact classification as the most common applications. Clustering and unsupervised methods were notably underrepresented compared to supervised models.

A recent article outlines recommended practices for data preprocessing in AI and machine learning models used for climate prediction, emphasizing the importance of data quality in generating accurate forecasts. The article aims to educate researchers and practitioners on the significant impact of preprocessing on model performance, particularly for predictions spanning subseasonal to decadal timescales.

A new analog computing method has been developed that significantly reduces the energy consumption associated with training artificial intelligence models, addressing the growing concern over the environmental impact of AI technologies. This innovation comes at a time when the energy demands of AI, such as those seen with ChatGPT, are under scrutiny, with estimates suggesting that a single query can consume as much energy as an average U.S. home does in a minute.