Sort by
Refine Your Search
-
estimation, confidence calibration, model routing, token selection, early exiting, adaptive visual processing, and efficient use of multiple foundation models. The work will combine algorithm development with
-
This research aims to design a sustainable framework for optimizing distributed computing systems to enhance performance while minimizing energy consumption. Existing scheduling algorithms often
-
scheduling, resource allocation, and workload placement algorithms for distributed AI training; Improve the communication efficiency, scalability, and reliability of decentralised training frameworks; Evaluate
-
Software function within SKA-Low delivers innovative systems that underpin telescope operations, including high-performance data processing platforms, large-scale distributed networks, and science data
-
Federated learning (FL) is an emerging machine learning paradium to enable distributed clients (e.g., mobile devices) to jointly train a machine learning model without pooling their raw data into a
-
healthcare application needs to analyze sensitive patient data across distributed nodes. Researchers and students can explore privacy-preserving algorithms and technologies like federated learning and zero
-
group of experts to predict (probabilistically) whether these occupations will be automated, augmented or unaffected by emerging technologies. Using this data, a classification algorithm is then trained
-
at one time. In non-stationary environments on the other hand, the same algorithms cannot be applied as the underlying data distributions change constantly and the same models are not valid. Hence, we need
-
estimation methods for deep neural networks. A principled Bayesian framework for multimodal uncertainty modeling. Robust learning algorithms under missing modalities and distribution shifts. New uncertainty
-
energy resources. The expected outcomes include technical advancement of distributed algorithms for managing energy resources at customer premises. The benefits include more resilient, secure, private, and