Sort by
Refine Your Search
-
TEC. 2. OBJECTIVES: Collaborate with clinical partners in data collection and annotation Design and implement new deep learning solutions for the analysis of heart sound auscultation, electrocardiogram
-
, energy consumption, and accuracy.; ; Training deep learning models, especially in LLMs, faces critical challenges that compromise the optimal use of GPUs. These bottlenecks result in poor computational
-
limited to, deep reinforcement learning, federated learning, deep learning and meta learning. The overall aim is to improve the efficiency in cyber-physical systems, such as drone swarms, that support 5G
-
workload’s data (e.g., Deep Learning, Large Language Models) while addressing the I/O interference and fairness challenges faced by current distributed infrastructures, where storage resources are being shared
-
benefit from health insurance, supported by INESC TEC. 2. OBJECTIVES: ● Research and develop novel reliable deep learning computer vision algorithms for the detection and quantification of GIM lesions
-
-of-the-art deep neural networks for musical audio, with special focus on timbre analysis and manipulation.; - Identify and implement approaches for explainable ML models.; - Cooperate in writing scientific
-
of programming and artificial intelligence.; - Knowledge of deep learning and computer vision.; - Autonomy. Minimum requirements: Strong knowledge of the English language (written and spoken). 5. EVALUATION
-
with a focus on traditional machine learning (shallow learning) and deep learning methodologies. Knowledge of Data Science, including the development of data analysis and visualisation pipelines. 5
-
, algorithms with a focus on traditional machine learning (shallow learning) and deep learning methodologies. Knowledge of Data Science, including the development of data analysis and visualisation pipelines. 5
-
benefit from health insurance, supported by INESC TEC. 2. OBJECTIVES: Research and develop novel reliable deep learning computer vision algorithms for the detection and quantification of GIM lesions