A5077867821- Advanced Memory and Neural Computing
- Ferroelectric and Negative Capacitance Devices
- Neural dynamics and brain function
- Neuroscience and Neural Engineering
- Photoreceptor and optogenetics research
- Neural Networks and Reservoir Computing
- CCD and CMOS Imaging Sensors
- EEG and Brain-Computer Interfaces
- Neural Networks and Applications
- Semiconductor materials and devices
- Cell Image Analysis Techniques
- Transition Metal Oxide Nanomaterials
- Quantum-Dot Cellular Automata
- Retinal Development and Disorders
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Cardiovascular and exercise physiology
- Advanced Graph Theory Research
- Energy Harvesting in Wireless Networks
- Machine Learning in Materials Science
- Physical Unclonable Functions (PUFs) and Hardware Security
- DNA and Biological Computing
- Single-cell and spatial transcriptomics
- Advanced Electron Microscopy Techniques and Applications
- Radiation Effects in Electronics
University of California, Santa Cruz
2020-2025
University of Michigan
2019-2024
University of California, San Diego
2024
The University of Western Australia
2016-2023
Michigan United
2023
University of California, Berkeley
2023
Hangzhou Dianzi University
2020-2022
The University of Sydney
2022
State Street (United States)
2022
Australian Research Council
2022
The brain is the perfect place to look for inspiration develop more efficient neural networks. inner workings of our synapses and neurons provide a glimpse at what future deep learning might like. This article serves as tutorial perspective showing how apply lessons learned from several decades research in learning, gradient descent, backpropagation, neuroscience biologically plausible spiking networks (SNNs). We also explore delicate interplay between encoding data spikes process;...
The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors has brought on new opportunities for applying both Spiking Neural Network (SNN) algorithms to healthcare biomedical applications at the edge.This can facilitate advancement medical Internet Things (IoT) systems Point Care (PoC) devices.In this paper, we provide a tutorial describing how various technologies including emerging memristive devices, Field Programmable Gate Arrays (FPGAs), Complementary Metal...
The application of hardware-based neural networks can be enhanced by integrating sensory neurons and synapses that enable direct input from external stimuli. This work reports optical control an oscillatory neuron based on volatile threshold switching in V
The ever‐increasing processing power demands of digital computers cannot continue to be fulfilled indefinitely unless there is a paradigm shift in computing. Neuromorphic computing, which takes inspiration from the highly parallel, low‐power, high‐speed, and noise‐tolerant computing capabilities brain, may provide such shift. Many researchers across academia industry have been studying materials, devices, circuits, systems, implement some functions networks neurons synapses develop...
The brain is the perfect place to look for inspiration develop more efficient neural networks. inner workings of our synapses and neurons provide a glimpse at what future deep learning might like. This paper serves as tutorial perspective showing how apply lessons learnt from several decades research in learning, gradient descent, backpropagation neuroscience biologically plausible spiking We also explore delicate interplay between encoding data spikes process; challenges solutions applying...
This paper presents the first experimental demonstration of a ternary memristor-CMOS logic family. We systematically design, simulate and experimentally verify primitive functions: AND, OR NOT gates. These are then used to build combinational NAND, NOR, XOR XNOR gates, as well data handling MAX MIN Our simulations performed using 50-nm process which verified with in-house fabricated indium-tin-oxide memristors, optimized for fast switching, high transconductance, low current leakage. obtain...
Memristive arrays are a natural fit to implement spiking neural network (SNN) acceleration. Representing information as digital events can improve noise margins and tolerance device variability compared analog bitline current summation approaches multiply–accumulate (MAC) operations. Restricting neuron activations single-bit spikes also alleviates the significant analog-to-digital converter (ADC) overhead that mixed-signal have struggled overcome. Binarized, more generally,...
As the size of large language models continue to scale, so does computational resources required run it. Spiking Neural Networks (SNNs) have emerged as an energy-efficient approach deep learning that leverage sparse and event-driven activations reduce overhead associated with model inference. While they become competitive non-spiking on many computer vision tasks, SNNs also proven be more challenging train. a result, their performance lags behind modern learning, we are yet see effectiveness...
Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for dynamics, there exists numerous software solutions stacks whose variability makes it difficult reproduce findings. Here, we establish common reference frame computations in digital systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines...
Spiking neural networks (SNN), also often referred to as the third generation of networks, carry potential for a massive reduction in memory and energy consumption over traditional, second-generation networks. Inspired by undisputed efficiency human brain, they introduce temporal neuronal sparsity, which can be exploited next-generation neuromorphic hardware. Energy plays crucial role many engineering applications, instance, structural health monitoring. Machine learning contexts, especially...
Abstract Biologically plausible computing systems require fine‐grain tuning of analog synaptic characteristics. In this study, lithium‐doped silicate resistive random access memory with a titanium nitride (TiN) electrode mimicking biological synapses is demonstrated. Biological plausibility RRAM device thought to occur due the low ionization energy lithium ions, which enables controllable forming and filamentary retraction spontaneously or under an applied voltage. The TiN can effectively...
We present and experimentally validate two minimal compact memristive models for spiking neuronal signal generation using commercially available low-cost components. The first neuron model is called the Memristive Integrate-and-Fire (MIF) model, signaling with voltage levels: spike-peak, rest-potential. second MIF2 also presented, which promotes local adaptation by accounting a third refractory level during hyperpolarization. show both are in terms of number circuit elements integration...
Abstract The vast majority of studies that process and analyze neural signals are conducted on cloud computing resources, which is often necessary for the demanding requirements deep network workloads. However, applications such as epileptic seizure detection stand to benefit from edge devices can securely sensitive medical data in a real-time personalised manner. In this work, we propose novel neuromorphic approach using surrogate gradient-based spiking (SNN), consists ConvLSTM unit. We...
In-memory computing (IMC) systems have great potential for accelerating data-intensive tasks such as deep neural networks (DNNs). As DNN models are generally highly proprietary, the network architectures become valuable targets attacks. In IMC systems, since whole model is mapped on chip and weight memory read can be restricted, pre-mapped acts a ``black box'' users. However, localized stationary data patterns may subject to other this paper, we propose side-channel attack methodology...
The development of a bioinspired image sensor, which can match the functionality vertebrate retina, has provided new opportunities for vision systems and processing through realization architectures. Research in both retinal cellular nanodriven memristive technology made challenging arena more accessible to emulate features retina that are closer biological systems. This paper synthesizes signal flow path photocurrent throughout scalable 180-nm CMOS technology, initiates at 128 × active...
Artificial neural networks have become ubiquitous in modern life, which has triggered the emergence of a new class application specific integrated circuits for their acceleration. ReRAM-based accelerators gained significant traction due to ability leverage in-memory computations. In crossbar structure, they can perform multiply-and-accumulate operations more efficiently than standard CMOS logic. By virtue being resistive switches, ReRAM switches only reliably store one two states. This is...
Spiking Neural Networks for Nonlinear RegressionAlexander Henkes a, Jason Eshraghian b, Henning Wessels aa TU Braunschweig, Germanyb UC Santa Cruz, 1156 High Street, 95064, United StatesProceedings of Neuromorphic Materials, Devices, Circuits and Systems (NeuMatDeCaS)València, Spain, 2023 January 23rd - 25thOrganizers: Rohit Abraham John, Irem Boybat, Simone FabianoContributed talk, Alexander Henkes, presentation 045DOI: https://doi.org/10.29363/nanoge.neumatdecas.2023.045Publication date:...
The field of neuromorphic computing holds great promise in terms advancing efficiency and capabilities by following brain-inspired principles. However, the rich diversity techniques employed research has resulted a lack clear standards for benchmarking, hindering effective evaluation advantages strengths methods compared to traditional deep-learning-based methods. This paper presents collaborative effort, bringing together members from academia industry, define benchmarks computing:...
Efficient communication is central to both biological and artificial intelligence (AI) systems. In brains, the challenge of long-range across regions addressed through sparse, spike-based signaling, minimizing energy consumption latency. contrast, modern AI workloads, which keep scaling ever larger distributed compute systems, are increasingly constrained by bandwidth limitations, creating bottlenecks that hinder scalability efficiency. Inspired brain's efficient strategies, we propose SNAP,...
Soil microbial fuel cells (SMFCs) are an emerging technology which offer clean and renewable energy in environments where more traditional power sources, such as chemical batteries or solar, not suitable. With further development, SMFCs show great promise for use robust affordable outdoor sensor networks, particularly farmers. One of the greatest challenges development this is understanding predicting fluctuations SMFC generation, electro-generative process yet fully understood. Very little...