Utku Emre Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Utku Emre Ali has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Harish Bhaskaran
Department of Materials, University of Oxford, Oxford, UK
3 shared publications - C. David Wright
Department of Engineering, University of Exeter, Exeter, UK
2 shared publications Xuan Li
Department of Materials, University of Oxford, Oxford, UK
2 shared publications- Bowei Dong
Department of Materials, University of Oxford, Oxford, UK
1 shared publication Dim-Lee Kwong
Institute of Microelectronics, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
1 shared publication- Gaurav Modi
Department of Materials Science and Engineering, University of Pennsylvania, Philadelphia, USA
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 19 October 2023
- Published by Springer Nature in Nature Photonics
- Vol. 17 (12) , 1080-1088
Higher-dimensional processing using a photonic tensor core with continuous-time data
New developments in hardware-based ‘accelerators’ range from electronic tensor cores and memristor-based arrays to photonic implementations. The goal of these approaches is to handle the exponentially growing computational load of machine learning, which currently requires the doubling of hardware capability approximately every 3.5 months. One solution is increasing the data dimensionality that is processable by such hardware. Although two-dimensional data processing by multiplexing space and wavelength has been previously reported, the use of three-dimensional processing has not yet been implemented in hardware. In this paper, we introduce the radio-frequency modulation of photonic signals to increase parallelization, adding an additional dimension to the data alongside spatially distributed non-volatile memories and wavelength multiplexing. We leverage higher-dimensional processing to configure such a system to an architecture compatible with edge computing frameworks. Our system achieves a parallelism of 100, two orders higher than implementations using only the spatial and wavelength degrees of freedom. We demonstrate this by performing a synchronous convolution of 100 clinical electrocardiogram signals from patients with cardiovascular diseases, and constructing a convolutional neural network capable of identifying patients at sudden death risk with 93.5% accuracy.
- 19 October 2023
- Published by Springer Nature in Nature Photonics
- Vol. 17 (12) , 1080-1088
Top Cited PapersOpen AccessHigher-dimensional processing using a photonic tensor core with continuous-time data
New developments in hardware-based ‘accelerators’ range from electronic tensor cores and memristor-based arrays to photonic implementations. The goal of these approaches is to handle the exponentially growing computational load of machine learning, which currently requires the doubling of hardware capability approximately every 3.5 months. One solution is increasing the data dimensionality that is processable by such hardware. Although two-dimensional data processing by multiplexing space and wavelength has been previously reported, the use of three-dimensional processing has not yet been implemented in hardware. In this paper, we introduce the radio-frequency modulation of photonic signals to increase parallelization, adding an additional dimension to the data alongside spatially distributed non-volatile memories and wavelength multiplexing. We leverage higher-dimensional processing to configure such a system to an architecture compatible with edge computing frameworks. Our system achieves a parallelism of 100, two orders higher than implementations using only the spatial and wavelength degrees of freedom. We demonstrate this by performing a synchronous convolution of 100 clinical electrocardiogram signals from patients with cardiovascular diseases, and constructing a convolutional neural network capable of identifying patients at sudden death risk with 93.5% accuracy.
- Open Access
- 14 July 2022
- Published by Optica Publishing Group in Optica
- Vol. 9 (7) , 792-802
Monadic Pavlovian associative learning in a backpropagation-free photonic network
Over a century ago, Ivan P. Pavlov, in a classic experiment, demonstrated how dogs can learn to associate a ringing bell with food, thereby causing a ring to result in salivation. Today, it is rare to find the use of Pavlovian type associative learning for artificial intelligence applications even though other learning concepts, in particular, backpropagation on artificial neural networks (ANNs), have flourished. However, training using the backpropagation method on “conventional” ANNs, especially in the form of modern deep neural networks, is computationally and energy intensive. Here, we experimentally demonstrate a form of backpropagation-free learning using a single (or monadic) associative hardware element. We realize this on an integrated photonic platform using phase-change materials combined with on-chip cascaded directional couplers. We then develop a scaled-up circuit network using our monadic Pavlovian photonic hardware that delivers a distinct machine learning framework based on single-element associations and, importantly, using backpropagation-free architectures to address general learning tasks. Our approach reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed while also offering a higher bandwidth inherent to our photonic implementation.
- 14 July 2022
- Published by Optica Publishing Group in Optica
- Vol. 9 (7) , 792-802
Open AccessMonadic Pavlovian associative learning in a backpropagation-free photonic network
Over a century ago, Ivan P. Pavlov, in a classic experiment, demonstrated how dogs can learn to associate a ringing bell with food, thereby causing a ring to result in salivation. Today, it is rare to find the use of Pavlovian type associative learning for artificial intelligence applications even though other learning concepts, in particular, backpropagation on artificial neural networks (ANNs), have flourished. However, training using the backpropagation method on “conventional” ANNs, especially in the form of modern deep neural networks, is computationally and energy intensive. Here, we experimentally demonstrate a form of backpropagation-free learning using a single (or monadic) associative hardware element. We realize this on an integrated photonic platform using phase-change materials combined with on-chip cascaded directional couplers. We then develop a scaled-up circuit network using our monadic Pavlovian photonic hardware that delivers a distinct machine learning framework based on single-element associations and, importantly, using backpropagation-free architectures to address general learning tasks. Our approach reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed while also offering a higher bandwidth inherent to our photonic implementation.
- Open Access
- 18 March 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-8
Real-time nanomechanical property modulation as a framework for tunable NEMS
Phase-change materials (PCMs) can switch between amorphous and crystalline states permanently yet reversibly. However, the change in their mechanical properties has largely gone unexploited. The most practical configuration using suspended thin-films suffer from filamentation and melt-quenching. Here, we overcome these limitations using nanowires as active nanoelectromechanical systems (NEMS). We achieve active modulation of the Young’s modulus in GeTe nanowires by exploiting a unique dislocation-based route for amorphization. These nanowire NEMS enable power-free tuning of the resonance frequency over a range of 30%. Furthermore, their high quality factors ( $$Q$$ > 104) are retained after phase transformation. We utilize their intrinsic piezoresistivity with unprecedented gauge factors (up to 1100) to facilitate monolithic integration. Our NEMS demonstrate real-time frequency tuning in a frequency-hopping spread spectrum radio prototype. This work not only opens up an entirely new area of phase-change NEMS but also provides a novel framework for utilizing functional nanowires in active mechanical systems.- 18 March 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-8
Open AccessReal-time nanomechanical property modulation as a framework for tunable NEMS
Phase-change materials (PCMs) can switch between amorphous and crystalline states permanently yet reversibly. However, the change in their mechanical properties has largely gone unexploited. The most practical configuration using suspended thin-films suffer from filamentation and melt-quenching. Here, we overcome these limitations using nanowires as active nanoelectromechanical systems (NEMS). We achieve active modulation of the Young’s modulus in GeTe nanowires by exploiting a unique dislocation-based route for amorphization. These nanowire NEMS enable power-free tuning of the resonance frequency over a range of 30%. Furthermore, their high quality factors ( $$Q$$ > 104) are retained after phase transformation. We utilize their intrinsic piezoresistivity with unprecedented gauge factors (up to 1100) to facilitate monolithic integration. Our NEMS demonstrate real-time frequency tuning in a frequency-hopping spread spectrum radio prototype. This work not only opens up an entirely new area of phase-change NEMS but also provides a novel framework for utilizing functional nanowires in active mechanical systems. - 11 August 2018
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 95, 126-138
Low sensitivity complex image rejection filter for GNSS receivers
- 11 August 2018
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 95, 126-138
Low sensitivity complex image rejection filter for GNSS receivers