Research focus:
This track investigates brain-inspired architectures and learning algorithms. The primary focus is on Spiking Neural Networks (SNNs) and continual learning.

Main activities:

• Simulation & Modeling: Design and simulate SNN architectures in Python.

• Algorithm Development: Implement and evaluate continual learning algorithms for SNNs.

• Analysis: Apply dynamical systems theory to the stability analysis of SNNs.

Desired background and skills:

• Strong foundation in Spiking Neural Networks (SNNs), synaptic plasticity, and neuromorphic computing concepts.

• Proficiency in Linear Algebra, Probability Theory, and Differential Equations (Dynamical Systems).

• Experience with Machine Learning (ML) algorithms.

• Advanced skills in Python (specifically NumPy) and experience with object-oriented programming.

Research focus:
This track emphasizes the design and evaluation of digital neuromorphic hardware architectures that support event-driven, asynchronous, and parallel computation. Projects involve FPGA-based prototyping of neuromorphic processors with the software-hardware co-design methodology.

Typical activities:

• Hardware Design: Designing digital microarchitectures (RTL) specifically optimized for Spiking Neural Networks (SNNs).

• Prototyping: Implementing and testing neuromorphic processors on FPGA platforms to validate theoretical models.

• Performance Analysis: Conducting functional verification and rigorous PPA (Power, Performance, and Area) evaluations to benchmark hardware efficiency.

Desired background and skills:

• Strong foundation in digital design, computer architecture, and von Neumann vs. non-von Neumann paradigms.

• Proficiency in RTL design using VHDL and/or SystemVerilog.

• Familiarity with FPGA tools and workflows.

• Experience in the hardware implementation of SNNs or event-based processing systems.

• Knowledge of hardware verification methodologies and power/timing analysis tools.

Research focus:
This track bridges the gap between theoretical algorithms and practical, end-user applications. Our goal is to deploy neuromorphic models and hardware to solve real-world problems, prioritizing superior energy efficiency and adaptability. Projects in this theme focus on translating biological principles into functional biomedical wearable/assistive technologies and Edge AI systems.

Typical activities:

• Applied Innovation: Designing and deploying Spiking Neural Networks (SNNs) for biomedical signal processing (e.g., EMG gesture recognition) and low-power control tasks.

• Benchmarking & Analysis: Conducting rigorous comparative studies to evaluate neuromorphic solutions against conventional AI in terms of accuracy, latency, adaptability, and power consumption.

• System Integration: Interfacing software models with neuromorphic simulators or hardware to demonstrate real-time processing capabilities.

Desired background and skills:

• Experience in biomedical signal processing, specifically with Electromyography (EMG) or similar time-series data.

• Strong programming skills in Python (NumPy, PyTorch, or TensorFlow).

• Experience simulating Spiking Neural Networks (SNNs) or working with event-based processing.

• Ability to design experiments, analyze performance metrics, and visualize complex data.