Novel Learning Algorithms for Neuromorphic Chips
Neuromorphic systems are based on the mechanisms of adaptation and learning, and are modeled after the plasticity of synapses and neural structures in biological systems. We explore various supervised and unsupervised learning algorithms (including event-based learning) optimized for implementation on hardware, on either analog or digital chips (or FPGA). We will test these learning algorithms on our general-purpose neuromorphic simulators such as the IFAT.

NeuroElectronic Hybrid System
This project aims to integrate biological neurons, developed using in vitro culture, with silicon neuronal circuits for machine learning tasks. This will pave the way to build a brain-machine interface, where our NeuroElectronic hybrid system could be directly interfaced to the nervous tissue and could communicate with the nervous system in its native “language” (i.e., spikes), with very low power constraints.

Machine Learning for IoT/Edge Computing

IoT or Edge devices have to be active at all times to ensure that it can detect events of interest. In most cases, the events of interest are infrequent or are rare, as a result most of these IoT systems integrate a pattern classifier to filter out false-positive events and hence in the process relax the communication requirements. Edge computing focuses on data processing at the source, leading to lower bandwidth requirement, more personal data integrity and lower latency for real-time operations, but with stringent power and area constraints. In this research area, we develop ultra-light machine learning algorithms and implement them on analog/digital ASIC or on FPGA. Such systems can be used to implement always-on smart wake-up modules to perform wake up operation only when voice command or certain event is detected.

ML Co-Processor Hardware for Neural Decoding on Edge
This theme develops hardware-friendly machine learning algorithms optimized for real-time neural decoding on low-power, compact edge devices. The focus is on decoding brain states like attention, intention, and motor movements from neural signals with high accuracy and minimal latency under computational constraints. The co-processor integrates with the neuromorphic front-end to create a complete System-on-Chip (SoC) solution, enabling efficient, portable neurofeedback.

Applications in Neurorehabilitation and Beyond
The lab’s BCI research will span diverse applications in healthcare, education, and entertainment from cognitive rehabilitation and motor recovery for patients with neurological conditions to adaptive learning systems leveraging BCI to personalize user interactions based on cognitive states. Additionally, the research explores advanced human-computer interfaces, creating intuitive systems powered by real-time brain activity. These efforts demonstrate the transformative potential of BCI technologies in bridging neuroscience and engineering for practical solutions.

This research aims to develop circuits and systems for biomedical applications. This work will be conducted in close collaboration with clinicians. We are also interested in developing the EEG based Brain-computer interface system for neurorehabilitation.

There lies a challenge when it comes to connecting classical electronics to these qubits. The qubits need high-frequency (GHz) electromagnetic signals for control and readout pulses in the order of a few tens of nanoseconds. The traditional setup for generation and capture of such signals is often costly and complex with many components. In this work, we address these challenges by developing a specific FPGA-based system that brings the functionality of all the traditional equipment onto a single board.