Subtopic Deep Dive
Ferroelectric Devices for Neuromorphic Computing
Research Guide
What is Ferroelectric Devices for Neuromorphic Computing?
Ferroelectric devices for neuromorphic computing use ferroelectric materials to emulate synaptic plasticity and neuronal dynamics through domain switching and analog conductance modulation.
This subtopic covers ferroelectric synapses and neurons enabling energy-efficient brain-inspired hardware. Key works demonstrate learning via ferroelectric domain dynamics (Boyn et al., 2017, 551 citations) and ultrathin domain switching for neuromorphic performance (Li et al., 2019, 222 citations). Over 10 papers from 2013-2023 explore these devices, with 920+ total citations in high-impact journals.
Why It Matters
Ferroelectric devices enable sub-nanosecond switching for low-power spiking neural networks, as shown in Ma et al. (2020, 281 citations) with Ag/BaTiO3/Nb:SrTiO3 tunnel junctions. They support synaptic weight updates in solid-state synapses (Boyn et al., 2017), reducing energy per operation below CMOS limits for edge AI. Wang et al. (2021, 312 citations) integrate 2D ferroelectric channels for ultra-fast memory-neural computing hybrids, accelerating scalable neuromorphic systems.
Key Research Challenges
Endurance in Domain Switching
Repeated ferroelectric switching degrades device endurance, limiting synaptic update cycles. Li et al. (2019) achieve reproducible ultrathin domain switching but note fatigue after 10^9 cycles. Boyn et al. (2017) report domain dynamics enabling learning yet constrained by retention.
Analog Precision Control
Achieving multi-level conductance states for precise synaptic weights remains difficult due to stochastic domain nucleation. Ma et al. (2020) demonstrate sub-ns memristors but highlight variability in analog updates. Wang et al. (2021) address this in 2D transistors with improved linearity.
Scalability to Networks
Integrating ferroelectric devices into large-scale neuromorphic arrays faces crosstalk and uniformity issues. Ielmini and Ambrogio (2019) discuss emerging devices needing array-level demonstrations. Schuman et al. (2022) emphasize hardware efficiency metrics for practical scaling.
Essential Papers
Opportunities for neuromorphic computing algorithms and applications
Catherine D. Schuman, Shruti Kulkarni, Maryam Parsa et al. · 2022 · Nature Computational Science · 920 citations
Deep Learning With Spiking Neurons: Opportunities and Challenges
Michael Pfeiffer, Thomas Pfeil · 2018 · Frontiers in Neuroscience · 688 citations
Spiking neural networks (SNNs) are inspired by information processing in biology, where sparse and asynchronous binary signals are communicated and processed in a massively parallel fashion. SNNs o...
Learning through ferroelectric domain dynamics in solid-state synapses
Sören Boyn, Julie Grollier, Gwendal Lecerf et al. · 2017 · Nature Communications · 551 citations
Two-dimensional ferroelectric channel transistors integrating ultra-fast memory and neural computing
Shuiyuan Wang, Lan Liu, Lurong Gan et al. · 2021 · Nature Communications · 312 citations
Emerging neuromorphic devices
Daniele Ielmini, Stefano Ambrogio · 2019 · Nanotechnology · 300 citations
Abstract Artificial intelligence (AI) has the ability of revolutionizing our lives and society in a radical way, by enabling machine learning in the industry, business, health, transportation, and ...
Sub-nanosecond memristor based on ferroelectric tunnel junction
Chao Ma, Zhen Luo, Weichuan Huang et al. · 2020 · Nature Communications · 281 citations
Abstract Next-generation non-volatile memories with ultrafast speed, low power consumption, and high density are highly desired in the era of big data. Here, we report a high performance memristor ...
Electrolyte-gated transistors for synaptic electronics, neuromorphic computing, and adaptable biointerfacing
Haifeng Ling, Dimitrios A. Koutsouras, Setareh Kazemzadeh et al. · 2020 · Applied Physics Reviews · 267 citations
Functional emulation of biological synapses using electronic devices is regarded as the first step toward neuromorphic engineering and artificial neural networks (ANNs). Electrolyte-gated transisto...
Reading Guide
Foundational Papers
Start with Boyn et al. (2017) for core domain dynamics in synapses; Li et al. (2019) for reproducible switching basics, building toward modern analogs.
Recent Advances
Study Wang et al. (2021) for 2D integration advances; Ma et al. (2020) for sub-ns speed; Schuman et al. (2022) for algorithm-device mapping.
Core Methods
Core techniques: ferroelectric tunnel junctions (Ma et al., 2020), domain wall motion for plasticity (Boyn et al., 2017), and analog conductance tuning in HfO2 devices (Li et al., 2019).
How PapersFlow Helps You Research Ferroelectric Devices for Neuromorphic Computing
Discover & Search
Research Agent uses searchPapers with query 'ferroelectric synapses neuromorphic' to retrieve Boyn et al. (2017), then citationGraph reveals 551 citing works on domain dynamics, and findSimilarPapers surfaces Li et al. (2019) for ultrathin switching comparisons.
Analyze & Verify
Analysis Agent applies readPaperContent on Ma et al. (2020) to extract sub-ns switching metrics, verifies claims via verifyResponse (CoVe) against Schuman et al. (2022), and runs PythonAnalysis with NumPy to plot endurance cycles from Li et al. (2019) data using GRADE for evidence strength.
Synthesize & Write
Synthesis Agent detects gaps in analog scalability between Boyn et al. (2017) and Wang et al. (2021), flags contradictions in stochasticity emulation; Writing Agent uses latexEditText for circuit diagrams, latexSyncCitations for 10+ references, and latexCompile for a review manuscript with exportMermaid for synaptic network graphs.
Use Cases
"Plot endurance vs. switching speed from ferroelectric neuromorphic papers"
Research Agent → searchPapers → Analysis Agent → runPythonAnalysis (pandas/matplotlib on data from Ma et al. 2020 and Li et al. 2019) → matplotlib figure of scatter plot with regression lines.
"Draft LaTeX section on ferroelectric synapses with citations"
Synthesis Agent → gap detection on Boyn et al. 2017 → Writing Agent → latexEditText + latexSyncCitations (10 papers) + latexCompile → compiled PDF section with equations and figures.
"Find code for ferroelectric domain simulation in neuromorphic papers"
Research Agent → paperExtractUrls on Boyn et al. 2017 → Code Discovery → paperFindGithubRepo → githubRepoInspect → Python simulation scripts for domain dynamics with usage examples.
Automated Workflows
Deep Research workflow scans 50+ papers via searchPapers on 'ferroelectric neuromorphic synapses', structures report with tables from Boyn et al. (2017) and Li et al. (2019) metrics. DeepScan applies 7-step CoVe analysis to Wang et al. (2021) transistor data, verifying linearity claims. Theorizer generates hypotheses on stochasticity from Ma et al. (2020) switching fused with Schuman et al. (2022) algorithms.
Frequently Asked Questions
What defines ferroelectric devices for neuromorphic computing?
They emulate synapses via ferroelectric domain switching for analog plasticity, as in Boyn et al. (2017) using domain dynamics for learning.
What are key methods in this subtopic?
Methods include ferroelectric tunnel junctions (Ma et al., 2020), 2D channel transistors (Wang et al., 2021), and ultrathin domain switching (Li et al., 2019).
What are the most cited papers?
Top papers are Boyn et al. (2017, 551 citations) on domain dynamics, Li et al. (2019, 222 citations) on reproducible switching, and Wang et al. (2021, 312 citations) on 2D transistors.
What open problems exist?
Challenges include endurance beyond 10^9 cycles, precise multi-level states, and array scalability, as noted in Ielmini and Ambrogio (2019) and Schuman et al. (2022).
Research Ferroelectric and Negative Capacitance Devices with AI
PapersFlow provides specialized AI tools for Engineering researchers. Here are the most relevant for this topic:
AI Literature Review
Automate paper discovery and synthesis across 474M+ papers
Paper Summarizer
Get structured summaries of any paper in seconds
Code & Data Discovery
Find datasets, code repositories, and computational tools
AI Academic Writing
Write research papers with AI assistance and LaTeX support
See how researchers in Engineering use PapersFlow
Field-specific workflows, example queries, and use cases.
Start Researching Ferroelectric Devices for Neuromorphic Computing with AI
Search 474M+ papers, run AI-powered literature reviews, and write with integrated citations — all in one workspace.
See how PapersFlow works for Engineering researchers