Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Ahmed, Soyed Tuhin"'
Autor:
Ahmed, Soyed Tuhin, Tahoori, Mehdi
The performance of deep learning algorithms such as neural networks (NNs) has increased tremendously recently, and they can achieve state-of-the-art performance in many domains. However, due to memory and computation resource constraints, implementin
Externí odkaz:
http://arxiv.org/abs/2405.18894
The applications of artificial intelligence (AI) are rapidly evolving, and they are also commonly used in safety-critical domains, such as autonomous driving and medical diagnosis, where functional safety is paramount. In AI-driven systems, uncertain
Externí odkaz:
http://arxiv.org/abs/2405.05286
Bayesian Neural Networks (BayNNs) naturally provide uncertainty in their predictions, making them a suitable choice in safety-critical applications. Additionally, their realization using memristor-based in-memory computing (IMC) architectures enables
Externí odkaz:
http://arxiv.org/abs/2401.12416
Internet of Things (IoT) and smart wearable devices for personalized healthcare will require storing and computing ever-increasing amounts of data. The key requirements for these devices are ultra-low-power, high-processing capabilities, autonomy at
Externí odkaz:
http://arxiv.org/abs/2401.06195
Autor:
Ahmed, Soyed Tuhin, Hefenbrock, Michael, Prenat, Guillaume, Anghel, Lorena, Tahoori, Mehdi B.
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making. Dropout-based BayNNs are increasingly implemented in spintronics-based computation-in-memory architectures for resource-constrain
Externí odkaz:
http://arxiv.org/abs/2401.04744
Autor:
Ahmed, Soyed Tuhin, tahoori, Mehdi B.
Neural networks (NNs) are increasingly used in always-on safety-critical applications deployed on hardware accelerators (NN-HAs) employing various memory technologies. Reliable continuous operation of NN is essential for safety-critical applications.
Externí odkaz:
http://arxiv.org/abs/2401.01458
Autor:
Ahmed, Soyed Tuhin, Danouchi, Kamal, Hefenbrock, Michael, Prenat, Guillaume, Anghel, Lorena, Tahoori, Mehdi B.
Uncertainty estimation in Neural Networks (NNs) is vital in improving reliability and confidence in predictions, particularly in safety-critical applications. Bayesian Neural Networks (BayNNs) with Dropout as an approximation offer a systematic appro
Externí odkaz:
http://arxiv.org/abs/2311.15816
Autor:
Ahmed, Soyed Tuhin, Danouchi, Kamal, Hefenbrock, Michael, Prenat, Guillaume, Anghel, Lorena, Tahoori, Mehdi B.
Recently, machine learning systems have gained prominence in real-time, critical decision-making domains, such as autonomous driving and industrial automation. Their implementations should avoid overconfident predictions through uncertainty estimatio
Externí odkaz:
http://arxiv.org/abs/2306.10185
Autor:
Ahmed, Soyed Tuhin, Tahoori, Mehdi B.
Neural networks (NNs) are capable of learning complex patterns and relationships in data to make predictions with high accuracy, making them useful for various tasks. However, NNs are both computation-intensive and memory-intensive methods, making th
Externí odkaz:
http://arxiv.org/abs/2305.09348
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.