1 citations · 2 across the 11 of their papers we have counts for
11 papers
From Ontology Conformance to Admissible Reconfiguration: A RoSO/SMGI Adequacy Argument for Robotic Service Governance
Aomar Osmani
The Robotic Service Ontology (RoSO) gives service robotics a typed semantic vocabulary for services, functions, interactions, and deployment-sensitive constraints. Its public revis…
General Machine Learning: Theory for Learning Under Variable Regimes
Aomar Osmani
We study learning under regime variation, where the learner, its memory state, and the evaluative conditions may evolve over time. This paper is a foundational and structural contr…
Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems
Théo Zangato, Aomar Osmani, Pegah Alizadeh
Meta-Reinforcement Learning addresses the critical limitations of conventional Reinforcement Learning in multi-task and non-stationary environments by enabling fast policy adaptati…
SMGI: A Structural Theory of General Artificial Intelligence
Aomar Osmani
We introduce SMGI, a structural theory of general artificial intelligence, and recast the foundational problem of learning from the optimization of hypotheses within fixed environm…
Data-Driven Policy Mapping for Safe RL-based Energy Management Systems
Theo Zangato, Aomar Osmani, Pegah Alizadeh
Increasing global energy demand and renewable integration complexity have placed buildings at the center of sustainable energy management. We present a three-step reinforcement lea…
Meta-Decomposition: Dynamic Segmentation Approach Selection in IoT-based Activity Recognition
Seyed M. R. Modaresi, Aomar Osmani, Mohammadreza Razzazi +1
Internet of Things (IoT) devices generate heterogeneous data over time; and relying solely on individual data points is inadequate for accurate analysis. Segmentation is a common p…
Boosting Medical Image Segmentation Performance with Adaptive Convolution Layer
Seyed M. R. Modaresi, Aomar Osmani, Mohammadreza Razzazi +1
Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditi…
On the Necessity of Metalearning: Learning Suitable Parameterizations for Learning Processes
Massinissa Hamidi, Aomar Osmani
In this paper we will discuss metalearning and how we can go beyond the current classical learning paradigm. We will first address the importance of inductive biases in the learnin…
Multi-Modal Evaluation Approach for Medical Image Segmentation
Seyed M. R. Modaresi, Aomar Osmani, Mohammadreza Razzazi +1
Manual segmentation of medical images (e.g., segmenting tumors in CT scans) is a high-effort task that can be accelerated with machine learning techniques. However, selecting the r…
Affinity-Based Hierarchical Learning of Dependent Concepts for Human Activity Recognition
Aomar Osmani, Massinissa Hamidi, Pegah Alizadeh
In multi-class classification tasks, like human activity recognition, it is often assumed that classes are separable. In real applications, this assumption becomes strong and gener…
Description of Structural Biases and Associated Data in Sensor-Rich Environments
Massinissa Hamidi, Aomar Osmani
In this article, we study activity recognition in the context of sensor-rich environments. We address, in particular, the problem of inductive biases and their impact on the data c…