Publications by authors named "Yoon Ho Jang"

Article Synopsis
  • - Aluminum scandium nitride (AlScN) shows great potential for future ferroelectric memories due to its high remanent charge density, but it requires thinner films to reduce the high coercive field for lower operating voltages.
  • - Thinner films encounter issues with significant leakage currents, which complicate their compatibility with existing CMOS fabrication methods.
  • - This study introduces a HfN bottom electrode that minimizes lattice mismatch and reduces leakage currents, allowing for a CMOS-compatible HfN/ASN/TiN structure that showcases ferroelectric properties even at thicknesses of 3 nm and decreases the coercive voltage to 4.35 V.
View Article and Find Full Text PDF

In-sensor computing has gained attention as a solution to overcome the von Neumann computing bottlenecks inherent in conventional sensory systems. This attention is due to the ability of sensor elements to directly extract meaningful information from external signals, thereby simplifying complex data. The advantage of in-sensor computing can be maximized with the sampling principle of a restricted Boltzmann machine (RBM) to extract significant features.

View Article and Find Full Text PDF

This study explores the stochastic and binary switching behaviors of a Ta/HfO/RuO memristor to implement a combined data mining approach for outlier detection and data clustering algorithms in a multi-functional memristive crossbar array. The memristor switches stochastically with high state dispersion in the stochastic mode and deterministically between two states with low dispersion in the binary mode, while they can be controlled by varying operating voltages. The stochastic mode facilitates the parallel generation of random hyperplanes in a tree structure, used to compress spatial information of the dataset in the Euclidian space into binary format, still retaining sufficient spatial features.

View Article and Find Full Text PDF

Precise event detection within time-series data is increasingly critical, particularly in noisy environments. Reservoir computing, a robust computing method widely utilized with memristive devices, is efficient in processing temporal signals. However, it typically lacks intrinsic thresholding mechanisms essential for precise event detection.

View Article and Find Full Text PDF

Due to its area and energy efficiency, a memristive crossbar array (CBA) has been extensively studied for various combinatorial optimization applications, from network problems to circuit design. However, conventional approaches include heavily burdening software fine-tuning for the annealing process. Instead, this study introduces the "in-materia annealing" method, where the inter-layer interference of vertically stacked memristive CBA is utilized as an annealing method.

View Article and Find Full Text PDF
Article Synopsis
  • The work introduces a thin-film transistor (TFT) using tin monoxide (SnO) for neuromorphic computing, showcasing its ability to create a physical reservoir.
  • The SnO TFT exhibits memory fading and nonlinearity, crucial for advanced computing, and its three-terminal design allows for more complex reservoir states compared to traditional two-terminal devices.
  • This SnO TFT reservoir demonstrates outstanding performance in key tests, achieving high accuracy in handwritten digit recognition and time-series predictions, while also enabling high integration due to a low fabrication temperature.
View Article and Find Full Text PDF
Article Synopsis
  • Modern graph datasets often suffer from complexity and uncertainties that traditional graph models can’t effectively handle.
  • This study presents a new model called C-PGM, which uses innovative memristor technology to provide fast and reliable probabilistic graph processing.
  • C-PGM has shown promising results in accurately estimating probabilities and performing the PageRank algorithm, while also reducing computational costs compared to standard methods.
View Article and Find Full Text PDF

In the big data era, the requirement for data clustering methods that can handle massive and heterogeneous datasets with varying distributions increases. This study proposes a clustering algorithm for data sets with heterogeneous density using a dual-mode memristor crossbar array for data clustering. The array consists of a Ta/HfO/RuO memristor operating in analog or digital modes, controlled by the reset voltage.

View Article and Find Full Text PDF

Neuromorphic computing promises an energy-efficient alternative to traditional digital processors in handling data-heavy tasks, primarily driven by the development of both volatile (neuronal) and nonvolatile (synaptic) resistive switches or memristors. However, despite their energy efficiency, memristor-based technologies presently lack functional tunability, thus limiting their competitiveness with arbitrarily programmable (general purpose) digital computers. This work introduces a two-terminal bilayer memristor, which can be tuned among neuronal, synaptic, and hybrid behaviors.

View Article and Find Full Text PDF

Bayesian networks and Bayesian inference, which forecast uncertain causal relationships within a stochastic framework, are used in various artificial intelligence applications. However, implementing hardware circuits for the Bayesian inference has shortcomings regarding device performance and circuit complexity. This work proposed a Bayesian network and inference circuit using a CuTe/HfO/Pt volatile memristor, a probabilistic bit neuron that can control the probability of being 'true' or 'false.

View Article and Find Full Text PDF

Nanodevice oscillators (nano-oscillators) have received considerable attention to implement in neuromorphic computing as hardware because they can significantly improve the device integration density and energy efficiency compared to complementary metal oxide semiconductor circuit-based oscillators. This work demonstrates vertically stackable nano-oscillators using an ovonic threshold switch (OTS) for high-density neuromorphic hardware. A vertically stackable GeSe OTS-oscillator (VOTS-OSC) is fabricated with a vertical crossbar array structure by growing GeSe film conformally on a contact hole structure using atomic layer deposition.

View Article and Find Full Text PDF

Compact but precise feature-extracting ability is core to processing complex computational tasks in neuromorphic hardware. Physical reservoir computing (RC) offers a robust framework to map temporal data into a high-dimensional space using the time dynamics of a material system, such as a volatile memristor. However, conventional physical RC systems have limited dynamics for the given material properties, restricting the methods to increase their dimensionality.

View Article and Find Full Text PDF

Graphs adequately represent the enormous interconnections among numerous entities in big data, incurring high computational costs in analyzing them with conventional hardware. Physical graph representation (PGR) is an approach that replicates the graph within a physical system, allowing for efficient analysis. This study introduces a cross-wired crossbar array (cwCBA), uniquely connecting diagonal and non-diagonal components in a CBA by a cross-wiring process.

View Article and Find Full Text PDF

Multiple switching modes in a TaO/HfO memristor are studied experimentally and numerically through a reservoir computing (RC) simulation to reveal the importance of nonlinearity and heterogeneity in the RC framework. Unlike most studies, where homogeneous reservoirs are used, heterogeneity is introduced by combining different behaviors of the memristor units. The chosen memristor for the reservoir units is based on a TaO/HfO bilayer, in which the conductances of the TaO and HfO layers are controlled by the oxygen vacancies and deep/shallow traps, respectively, providing both volatile and non-volatile resistive switching modes.

View Article and Find Full Text PDF

In-sensor reservoir computing (RC) is a promising technology to reduce power consumption and training costs of machine vision systems by processing optical signals temporally. This study demonstrates a high-dimensional in-sensor RC system with optoelectronic memristors to enhance the performance of the in-sensor RC system. Because optoelectronic memristors can respond to both optical and electrical stimuli, optical and electrical masks are proposed to improve the dimensionality and performance of the in-sensor RC system.

View Article and Find Full Text PDF
Article Synopsis
  • - Memristor-based physical reservoir computing (RC) struggles to effectively process complex data because traditional methods assign only one input to each memristor, which limits capturing spatial relationships.
  • - A new "graph reservoir" system is introduced, utilizing a metal cell in a diagonal-crossbar array (mCBA) with dynamic memristors to better store and represent correlations between input signals.
  • - This innovative approach yields impressive results, achieving a 0.09 error rate in time series prediction, 97.21% accuracy in recognizing handwritten digits (MNIST), and 80.0% accuracy in diagnosing human brain connectivity.
View Article and Find Full Text PDF
Article Synopsis
  • - The study addresses the challenge of analyzing dynamic, interconnected big data represented as non-Euclidean graphs, where conventional methods struggle to find effective similarities between nodes.
  • - Researchers propose mapping these non-Euclidean graphs to a crossbar array (CBA) of memristors, utilizing sneak current to identify node similarities and predicting future connections, community connectivity, and brain neural connections.
  • - By connecting the CBA's bit lines to ground, the sneak current can be suppressed for adjacent node searches, demonstrating a physical computation method that mitigates typical issues faced with memristors.
View Article and Find Full Text PDF
Article Synopsis
  • A new computing scheme is needed to tackle complex tasks in the growing field of big data, and probabilistic computing (p-computing) offers a solution using probabilistic bits (p-bits).
  • This study introduces p-computing through the behavior of a specific type of memristor known as CuTe/HfO/Pt (CTHP), which utilizes threshold switching for its operations.
  • The p-bits created from these memristors can represent '0' or '1' with a probability influenced by input voltage, allowing for the execution of all 16 Boolean logic operations, as well as more complex tasks like full addition and factorization.
View Article and Find Full Text PDF

Recent advances in physical reservoir computing, which is a type of temporal kernel, have made it possible to perform complicated timing-related tasks using a linear classifier. However, the fixed reservoir dynamics in previous studies have limited application fields. In this study, temporal kernel computing was implemented with a physical kernel that consisted of a W/HfO/TiN memristor, a capacitor, and a resistor, in which the kernel dynamics could be arbitrarily controlled by changing the circuit parameters.

View Article and Find Full Text PDF