arXiv subjects

Seokjun Kim

Publications and source records attributed to Seokjun Kim.

5 recordsLinked to original sources

arXiv2026

Non-Local Metasurface-aided Leaky-Wave Antennas

This work presents a non-local terahertz metasurface integrated into a leaky-wave antenna for robust, wide-angle beam steering. The metasurface encodes a holographic pattern by explicitly inducing tangential and normal susceptibilities, along with magnetoelectric coupling. This design maintains stable radiation performance even when the longitudinal wavenumber of the incident guided mode - and thus its effective impinging angle - varies as a function of frequency. In particular, we show that there exists a limit to achieving exact angular insensitivity and propose an optimization-based framework to obtain the required susceptibilities that closely approximate near angle-insensitive performance for stable beam-steering performance. Additionally, an iterative synthesis approach is introduced that maps abstract susceptibilities to physically realizable structures. Full-wave simulations demonstrate a beam-scanning range of nearly 50 degrees over the 2.0-2.7 THz band - a more than threefold improvement over conventional local-metasurface designs.

physics.app-ph↗

arXiv2021

Imagine Networks

In this paper, we introduce an imagine network that can simulate itself through artificial association networks. Association, deduction, and memory networks are learned, and a network is created by combining the discriminator and reinforcement learning models. This model can learn various datasets or data samples generated in environments and generate new data samples.

cs.AI↗

arXiv2021

Memory Association Networks

We introduce memory association networks(MANs) that memorize and remember any data. This neural network has two memories. One consists of a queue-structured short-term memory to solve the class imbalance problem and long-term memory to store the distribution of objects, introducing the contents of storing and generating various datasets.

cs.AI↗

arXiv2021

Deductive Association Networks

we introduce deductive association networks(DANs), a network that performs deductive reasoning. To have high-dimensional thinking, combining various axioms and putting the results back into another axiom is necessary to produce new relationships and results. For example, it would be given two propositions: "Socrates is a man." and "All men are mortals." and two propositions could be used to infer the new proposition, "Therefore Socrates is mortal.". To evaluate, we used MNIST Dataset, a handwritten numerical image dataset, to apply it to the group theory and show the results of performing deductive learning.

cs.AI↗

arXiv2021

All-In-One: Artificial Association Neural Networks

Most deep learning models are limited to specific datasets or tasks because of network structures using fixed layers. In this paper, we discuss the differences between existing neural networks and real human neurons, propose association networks to connect existing models, and describe multiple types of deep learning exercises performed using a single structure. Further, we propose a new neural data structure that can express all basic models of existing neural networks in a tree structure. We also propose an approach in which information propagates from leaf to a root node using the proposed recursive convolution approach (i.e., depth-first convolution) and feed-forward propagation is performed. Thus, we design a ``data-based,'' as opposed to a ``model-based,'' neural network. In experiments conducted, we compared the learning performances of the models specializing in specific domains with those of models simultaneously learning various domains using an association network. The model learned well without significant performance degradation compared to that for models performing individual learning. In addition, the performance results were similar to those of the special case models; the output of the tree contained all information from the tree. Finally, we developed a theory for using arbitrary input data and learning all data simultaneously.

cs.AI↗