Zobrazeno 1 - 10
of 1 097
pro vyhledávání: '"YILDIRIM, Mustafa"'
Autor:
Oguz, Ilker, Dinc, Niyazi Ulas, Yildirim, Mustafa, Ke, Junjie, Yoo, Innfarn, Wang, Qifei, Yang, Feng, Moser, Christophe, Psaltis, Demetri
Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output, creating sign
Externí odkaz:
http://arxiv.org/abs/2407.10897
Autonomous driving is a complex task which requires advanced decision making and control algorithms. Understanding the rationale behind the autonomous vehicles' decision is crucial to ensure their safe and effective operation on highway driving. This
Externí odkaz:
http://arxiv.org/abs/2405.13547
Autor:
Zhou, Yi, Hsieh, Jih-Liang, Oguz, Ilker, Yildirim, Mustafa, Dinc, Niyazi Ulas, Gigli, Carlo, Wong, Kenneth K. Y., Moser, Christophe, Psaltis, Demetri
Electronic computers have evolved drastically over the past years with an ever-growing demand for improved performance. However, the transfer of information from memory and high energy consumption have emerged as issues that require solutions. Optica
Externí odkaz:
http://arxiv.org/abs/2403.02452
Artificial Intelligence (AI) demands large data flows within datacenters, heavily relying on multicasting data transfers. As AI models scale, the requirement for high-bandwidth and low-latency networking compounds. The common use of electrical packet
Externí odkaz:
http://arxiv.org/abs/2401.14173
Autor:
Yildirim, Mustafa, Fallah, Saber
This paper proposes a imitation learning model for autonomous driving on highway traffic by mimicking human drivers' driving behaviours. The study utilizes the HighD traffic dataset, which is complex, high-dimensional, and diverse in vehicle variatio
Externí odkaz:
http://arxiv.org/abs/2310.02477
Deep neural networks have achieved remarkable breakthroughs by leveraging multiple layers of data processing to extract hidden representations, albeit at the cost of large electronic computing power. To enhance energy efficiency and speed, the optica
Externí odkaz:
http://arxiv.org/abs/2307.08533
Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach
The dynamic nature of driving environments and the presence of diverse road users pose significant challenges for decision-making in autonomous driving. Deep reinforcement learning (DRL) has emerged as a popular approach to tackle this problem. Howev
Externí odkaz:
http://arxiv.org/abs/2307.01316
Autor:
Oguz, Ilker, Ke, Junjie, Wang, Qifei, Yang, Feng, Yildirim, Mustafa, Dinc, Niyazi Ulas, Hsieh, Jih-Liang, Moser, Christophe, Psaltis, Demetri
Neural networks (NN) have demonstrated remarkable capabilities in various tasks, but their computation-intensive nature demands faster and more energy-efficient hardware implementations. Optics-based platforms, using technologies such as silicon phot
Externí odkaz:
http://arxiv.org/abs/2305.19170
Autor:
Yildirim, Mustafa, Mozaffari, Sajjad, McCutcheon, Luc, Dianati, Mehrdad, Fallah, Alireza Tamaddoni-Nezhad Saber
Autonomous driving decision-making is a challenging task due to the inherent complexity and uncertainty in traffic. For example, adjacent vehicles may change their lane or overtake at any time to pass a slow vehicle or to help traffic flow. Anticipat
Externí odkaz:
http://arxiv.org/abs/2209.02106
Autor:
Yildirim, Mustafa, Oguz, Ilker, Kaufmann, Fabian, Escale, Marc Reig, Grange, Rachel, Psaltis, Demetri, Moser, Christophe
Modern machine learning models use an ever-increasing number of parameters to train (175 billion parameters for GPT-3) with large datasets to obtain better performance. Bigger is better has been the norm. Optical computing has been reawakened as a po
Externí odkaz:
http://arxiv.org/abs/2208.09398