• Home Systems & Design Low Power - High Performance Manufacturing, Packaging & Materials Test, Measurement & Analytics Auto, Security & Enabling Technologies Special Reports Business & Startups Jobs Knowledge Center Technical PapersHome’;AI/ML/DLArchitecturesAutomotive/ AerospaceCommunication/Data MovementDesign & VerificationLithographyManufacturingMaterialsMemoryOptoelectronics / PhotonicsPackagingPower & PerformanceQuantumSecurityTest, Measurement, Analytics tech papersTransistorsZ-End Applications Home AI/ML/DL Architectures Automotive/ Aerospace Communication/Data Movement Design & Verification Lithography Manufacturing Materials Memory Optoelectronics / Photonics Packaging Power & Performance Quantum Security Test, Measurement, Analytics tech papers Transistors Z-End Applications Events & WebinarsEventsWebinars Events Webinars Videos & ResearchVideosIndustry Research Videos Industry Research Newsletters & StoreNewslettersStore Newsletters Store MENUHomeSpecial ReportsSystems & DesignLow Power-High PerformanceManufacturing, Packaging & MaterialsTest, Measurement & AnalyticsAuto, Security & Enabling TechnologiesKnowledge CenterVideosStartup CornerBusiness & StartupsJobsTechnical PapersEventsWebinarsIndustry ResearchNewslettersStoreSpecial Reports Home Special Reports Systems & Design Low Power-High Performance Manufacturing, Packaging & Materials Test, Measurement & Analytics Auto, Security & Enabling Technologies Knowledge Center Videos Startup Corner Business & Startups Jobs Technical Papers Events Webinars Industry Research Newsletters Store Special Reports ReRAM-based Neo-Hebbian Synapses For Training Neuromorphic HW (IIT Madras, UCSB) A new technical paper, “NeoHebbian synapses to accelerate online training of neuromorphic hardware,” was published by researchers at IIT Madras and UC Santa Barbara. • Abstract"Neuromorphic systems that employ advanced synaptic learning rules, such as the three-factor learning rule, require synaptic devices of increased complexit

Article Summaries:

  • Researchers from IIT Madras and UC Santa Barbara have introduced a novel ReRAM‑based synapse-termed NeoHebbian-that supports advanced neuromorphic learning rules. The device encodes a neuron‑coupling weight in its conductance and an eligibility trace in its local temperature, the latter modulated by voltage‑driven heating. Experimental validation demonstrates the synapse’s ability to implement three‑factor learning, tested on recurrent spiking neural networks using the e‑prop algorithm for temporal classification and on feedforward networks for reinforcement‑learning path planning. System‑level simulations, accounting for device non‑idealities, indicate that NeoHebbian synapses enable fast, compact, and energy‑efficient online training of neuromorphic hardware.
  • Researchers from IIT Madras and UC Santa Barbara have introduced a novel ReRAM‑based “NeoHebbian” synapse designed to accelerate online training of neuromorphic hardware. The device encodes two state variables: a conductance‑based coupling weight and an eligibility trace stored in the local temperature of the ReRAM, modulated by voltage‑driven heating. Experiments demonstrate its effectiveness on two tasks-temporal signal classification with recurrent spiking neural networks using the e‑prop algorithm, and reinforcement‑learning path planning in feedforward networks. System‑level simulations that include device non‑idealities confirm that these synapses enable fast, compact, and energy‑efficient implementation of advanced learning rules in neuromorphic systems.

Sources: