Postdoc project Integration of Organic Neuromorphic Devices for Smart Biosensors

Updated: 3 months ago
Deadline: 13 Feb 2022

Project

Brain-inspired (neuromorphic) computing aims to mimic the efficiency of the brain in complex classification tasks by applying learning directly in hardware and has great potential for local edge computing in applications such as smart wearables and point-of-care devices. Successful implementation requires straightforward training and low power operation and despite the emergence of organic materials as building blocks for neuromorphic systems by virtue of their low operation voltage and excellent tunability properties, these systems still rely on external training in software.

In the ERC project BIOMORPHIC we are developing trainable smart biosensors based on arrays of organic neuromorphic devices, acting as synaptic weights of a hardware neural network, directly on the chip.  Combined with their relative stability and low voltage operation these materials are ideal for local and autonomous operation. The goal of the project is to exploit the strength of machine-learning to efficiently classify biological cells through a modular microfluidic chip linked with the neuromorphic array, where input is generated by a range of integrated sensors optimized for characterizing various cell properties. In particular, BIOMORPHIC will be applied to classify circulation tumour cells (CTCs), known for their large variation in morphological and molecular properties making it difficult for conventional sensors to properly identify them.

In this postdoc project, relatively small arrays will be used for simple learning and classification tasks, related to the cell classification chip. The neuromorphic core will be trained to react to different sensor inputs from the surrounding including impedance, reflection, etc. and bases its decisions on this. The overall goal of this project is:

To develop a trainable smart lab-on-a-chip with integrated organic neuromorphic devices for cell classification.

Embedding
The postdoc will be directly supervised by dr.ir. Yoeri van de Burgt, associate professor in Neuromorphic Engineering, within the Microsystems section. The neuromorphic engineering group is part of the Institute for Complex Molecular Systems (ICMS) as well as the Eindhoven Artificial Intelligence Systems Institute (EAISI). The Microsystems section manages the Microfab lab, a state-of-the-art micro fabrication facility that houses a range of micro-manufacturing technologies. The project is part of the ERC Starting Grant project BIOMORPHIC.


View or Apply

Similar Positions