Neuromorphic & AI Hardware with Nanomaterials: Memristors, RRAM & Synaptic Devices

To provide foundational and applied knowledge in neuromorphic computing hardware using nanomaterials, focusing on memristive and resistive switching devices for energy-efficient AI systems.

• Understand the fundamentals of neuromorphic computing and brain-inspired architectures.
• Explore the physics and switching mechanisms of memristors and RRAM devices.
• Learn the role of nanomaterials in enabling synaptic plasticity and non-volatile memory behavior.
• Analyze structure–property relationships in nanoscale resistive devices.
• Understand fabrication techniques and material selection for synaptic hardware.
• Study AI–hardware co-design principles for edge and low-power computing.
• Examine device characterization parameters such as endurance, retention, switching speed, and variability.
• Explore integration of memristive devices into neural network architectures.
• Discuss challenges in scalability, reliability, and commercialization of neuromorphic hardware.
• Identify emerging research directions in intelligent, adaptive, and energy-efficient computing systems.

• Limits of von Neumann architecture and memory bottlenecks
• Introduction to neuromorphic computing principles
• Chua’s memristor theory and I–V hysteresis characteristics
• Resistive switching mechanisms: filamentary vs interface-type
• Nanomaterials in memristive devices: Metal oxides (TiO₂, HfO₂), Perovskites, 2D materials (MoS₂, graphene), CNTs & hybrid nanocomposites
• RRAM basics: SET/RESET physics, endurance, retention
• Crossbar arrays for in-memory analog computation
• Tools: Python, NumPy, Matplotlib, SciPy, Jupyter/Colab

Day 2: Synaptic Devices & Hardware-Aware AI Modeling

• Biological vs artificial synapses
• STDP (Spike-Timing Dependent Plasticity)
• Long-Term Potentiation (LTP) & Depression (LTD)
• Mapping neural weights to device conductance states
• 1R vs 1T1R structures
• Sneak path problem in crossbars
• Analog MAC (Multiply-Accumulate) operations in hardware
• Tools: Python, NumPy, PyTorch (intro), Nengo (neuromorphic simulator), Matplotlib

• Deep learning on memristive crossbars
• Device non-idealities: non-linearity, drift, stochastic switching
• Quantization and precision trade-offs
• CMOS integration challenges
• Edge AI & event-driven architectures
• Overview of commercial neuromorphic chips
• Tools: TensorFlow/PyTorch (intro), Nengo, NumPy, Scikit-learn (for benchmarking), Jupyter/Colab

By the end of the workshop, participants will be able to:

• Explain the operating principles of memristive and resistive switching devices.
• Relate nanomaterial properties to device performance metrics.
• Interpret I–V characteristics and switching behavior in synaptic devices.
• Understand hardware implementation of artificial neural networks.
• Evaluate the potential of neuromorphic systems for low-power AI applications.
• Propose conceptual designs for nanoscale AI hardware systems.

• Doctoral Scholars & Researchers: PhD candidates seeking to integrate computational workflows into their molecular research.
• Postdoctoral Fellows: Early-career scientists aiming to enhance their data-driven publication profile.
• University Faculty: Professors and HODs interested in modern bioinformatics pedagogy and tool mastery.
• Industry Scientists: R&D professionals from the Biotechnology and Pharmaceutical sectors transitioning to genomic-driven discovery.
• Postgraduate Students: Final-year PG students looking for specialized research-grade exposure beyond standard curricula.