Related papers: Deep learning empowered synthetic dimension dynami…

We show that in addition to providing effective and competitive closures, when analysed in terms of dynamics and physically-relevant diagnostics, artificial neural networks (ANNs) can be both interpretable and provide useful insights in the…

Geometrical dimensionality plays a fundamentally important role in the topological effects arising in discrete lattices. While direct experiments are limited by three spatial dimensions, the research topic of synthetic dimensions…

The synthetic dimension, a research topic of both fundamental significance and practical applications, is attracting increasing attention in recent years. In this paper, we propose a theoretical framework to construct arbitrary synthetic…

We introduce a simple scheme to implement synthetic dimensions in ultracold atomic gases, which only requires two basic and ubiquitous ingredients: the harmonic trap, which confines the atoms, combined with a periodic shaking. In our…

Recent progress in artificial intelligence (AI) has been driven by insights from physics and neuroscience, particularly through the development of artificial neural networks (ANNs) capable of complex cognitive tasks such as vision and…

Synthetic dimensions provide a powerful approach for simulating condensed matter physics in cold atoms and photonics, whereby a set of discrete degrees of freedom are coupled together and re-interpreted as lattice sites along an artificial…

Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs composed of more than one hidden-layer. On the other, there is no way to evolve…

As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic…

Autonomous construction of deep neural network (DNNs) is desired for data streams because it potentially offers two advantages: proper model's capacity and quick reaction to drift and shift. While the self-organizing mechanism of DNNs…

In the field of quantum simulation of condensed matter phenomena by artificially engineering the Hamiltonian of an atomic, molecular or optical system, the concept of `synthetic dimensions' has recently emerged as a powerful way to emulate…

Synthetic frequency dimension offers a powerful approach to simulate lattice models and control photon dynamics. However, extending this concept into the quantum regime, particularly at the single-photon level, has remained challenging in…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Large-scale deep neural networks consume expensive training costs, but the training results in less-interpretable weight matrices constructing the networks. Here, we propose a mode decomposition learning that can interpret the weight…

Spiking neural networks (SNNs) are biology-inspired artificial neural networks (ANNs) that comprise of spiking neurons to process asynchronous discrete signals. While more efficient in power consumption and inference speed on the…

Artificial Neural Networks (ANN) have gained significant popularity thanks to their ability to learn using the well-known backpropagation algorithm. Conversely, Spiking Neural Networks (SNNs), despite having broader capabilities than ANNs,…

Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on neuromorphic hardware are often considered for…

Recurrent neural networks (RNNs) are a class of neural networks that have emerged from the paradigm of artificial intelligence and has enabled lots of interesting advances in the field of natural language processing. Interestingly, these…

In recent years, the development of nanophotonic devices has presented a revolutionary means to manipulate light at nanoscale. Recently, artificial neural networks (ANNs) have displayed powerful ability in the inverse design of nanophotonic…

Over the past decade, artificial neural networks (ANNs) have made tremendous advances, in part due to the increased availability of annotated data. However, ANNs typically require significant power and memory consumptions to reach their…

Deep learning (DL) is a powerful tool that can solve complex problems, and thus, it seems natural to assume that DL can be used to enhance the security of wireless communication. However, deploying DL models to edge devices in wireless…