3 PhD's on Spiking integrated photonics for neuromorphic sensing and processing
3 PhD's on Spiking integrated photonics for neuromorphic sensing and processing
You cannot apply for this job anymore (deadline was 7 Apr 2024).
Browse the current job offers or choose an item in the top navigation above.
Job description
Would you like to perform cutting-edge research at the intersection between IC hardware and artificial intelligence? Do you want to explore a new class of electronic-photonic components that mimics how biological neurons behave and helps reduce energy consumption and increase performance for AI hardware accelerators? Then you should read on and consider one of the three PhD positions we offer here.
Job Description
Background
Rapid advances in artificial intelligence technologies have led to powerful models and algorithms that have revolutionized many applications across all fields of science and technology. Deep learning performed within artificial neural networks has yielded new ways to process data, leading to sophisticated systems with impressive functionality and benefits. However, conventional computing hardware is reaching its limits in terms of energy efficiency and speed. A new approach to computing hardware is needed. Novel brain-inspired or neuromorphic chips working with biologically inspired spiking neural networks have gained attention as they promise highly efficient ways to process data. Important research effort has been dedicated to develop such neuromorphic systems in electronic and photonic hardware. We offer three PhD positions in this fast-paced research field, embedded within a world-class research group.
The integrated photonics field
Similar to electronic ICs, PICs are revolutionizing areas such as healthcare, communication and sensing, and have the potential to be disruptive to the whole society. Novel PIC components will have a big impact on the fields of sensing and processing. A diversity of PIC-based sensors have been proposed in the last years, such as environmental sensors (e.g. gas sensing), medical sensors (e.g. optical coherence tomography), fiber Bragg grating sensors for temperature or strain measurement, light detection and ranging (LiDAR) and others. Equally, novel PIC based solutions for processing data and performing computation had been proposed for information transport (equalization, pulse shaping), sensory data processing (Radar, LiDAR) and algorithmic problem solving (optimization, neural networks). Figure 1: Photonic integrated circuits on a semiconductor wafer.Recently, a new field of neuromorphic photonics is emerging, which aims to build artificial opto-electronic neurons that mimic the brain for processing information based on synaptic processes. Taking advantage of their threshold-based characteristics, neuromorphic photonic devices can also be used for spike-based processing and event-based sensing to allow recognition of patterns in an ultra-fast and energy-efficient manner.
We have made initial steps towards implementing opto-electronic neurons in InP integrated photonics. We demonstrated a first generation of resonant tunneling diodes (RTD), which display electrical excitable characteristics via tunneling effects. Full opto-electronic neuromorphic behavior was demonstrated by coupling the RTD with off-the-shelf external laser devices in cooperation with partners. See M. Hejda et.al. Nanophotonics 12(5), 2022.
In parallel, we have investigated novel concepts to create all-optical neurons in InP integrated photonics. We demonstrated a class of laser-based optical neurons that exhibit random self-spiking, similar to what biological neurons do, but at much faster time scales. We also predict all-optical excitability for such laser neurons. See L. Puts et al., JSTQE 59(3), 2023.
We are now interested to pursue the monolithic integration of RTDs with lasers and other synaptic weighting devices to form electronic-photonic neurons on chip, thereby setting the grounds for future large-scale neuromorphic circuits. The PhD positions link to a new European collaborative project SPIKEPro (Spiking Photonic-Electronic IC for Quick and Efficient Processing) within the European Innovation Council (EIC) framework. Close collaboration with the project partners, University of Strathclyde, University College London, TU Ilmenau and Hewlett-Packard Labs is foreseen.
The PhD positions
Position 1 (Focus: sensing)
This research focuses on the investigation of RTD-based neuromorphic photodetectors capable of producing threshold-based electrical spikes upon receiving low-amplitude optical stimuli. Their integration with other waveguide-based photonic components will be explored as well. This position will aim at proof-of-principle demonstration of spike-based neuromorphic sensing (e.g. event-based sensing).
Position 2 (Focus: sensing)
This research focuses on the investigation of RTD-based neuromorphic lasers capable of producing threshold-based optical spikes upon receiving low-amplitude electrical stimuli. Their integration with other waveguide-based photonic components will be explored as well. This position will aim at proof-of-principle demonstration of spike-based processing in smart sensing concepts.
Position 3 (Focus: processing)
This research focuses on the investigation of micro-disk type lasers with saturable absorbers, capable of producing low-energy spikes when receiving low-energy optical signals. Novel memristive devices for electric and photonic weighting function will be explored and co-integrated with such all-optical laser neurons. The position will aim at proof-of-concept demonstration of ultra-fast optical spike processing.
In all the positions, the work will comprise concept development, device design (incl. optical and electrical simulations), photonic chip layout, cleanroom fabrication and chip characterization in our laboratories. You will be part of the Photonic Integration (PhI) research group within the Eindhoven Hendrik Casimir Institute (EHCI). The research will be done in collaboration with European partners from academia and industry.
Job Description
Background
Rapid advances in artificial intelligence technologies have led to powerful models and algorithms that have revolutionized many applications across all fields of science and technology. Deep learning performed within artificial neural networks has yielded new ways to process data, leading to sophisticated systems with impressive functionality and benefits. However, conventional computing hardware is reaching its limits in terms of energy efficiency and speed. A new approach to computing hardware is needed. Novel brain-inspired or neuromorphic chips working with biologically inspired spiking neural networks have gained attention as they promise highly efficient ways to process data. Important research effort has been dedicated to develop such neuromorphic systems in electronic and photonic hardware. We offer three PhD positions in this fast-paced research field, embedded within a world-class research group.
The integrated photonics field
Similar to electronic ICs, PICs are revolutionizing areas such as healthcare, communication and sensing, and have the potential to be disruptive to the whole society. Novel PIC components will have a big impact on the fields of sensing and processing. A diversity of PIC-based sensors have been proposed in the last years, such as environmental sensors (e.g. gas sensing), medical sensors (e.g. optical coherence tomography), fiber Bragg grating sensors for temperature or strain measurement, light detection and ranging (LiDAR) and others. Equally, novel PIC based solutions for processing data and performing computation had been proposed for information transport (equalization, pulse shaping), sensory data processing (Radar, LiDAR) and algorithmic problem solving (optimization, neural networks). Figure 1: Photonic integrated circuits on a semiconductor wafer.Recently, a new field of neuromorphic photonics is emerging, which aims to build artificial opto-electronic neurons that mimic the brain for processing information based on synaptic processes. Taking advantage of their threshold-based characteristics, neuromorphic photonic devices can also be used for spike-based processing and event-based sensing to allow recognition of patterns in an ultra-fast and energy-efficient manner.
We have made initial steps towards implementing opto-electronic neurons in InP integrated photonics. We demonstrated a first generation of resonant tunneling diodes (RTD), which display electrical excitable characteristics via tunneling effects. Full opto-electronic neuromorphic behavior was demonstrated by coupling the RTD with off-the-shelf external laser devices in cooperation with partners. See M. Hejda et.al. Nanophotonics 12(5), 2022.
In parallel, we have investigated novel concepts to create all-optical neurons in InP integrated photonics. We demonstrated a class of laser-based optical neurons that exhibit random self-spiking, similar to what biological neurons do, but at much faster time scales. We also predict all-optical excitability for such laser neurons. See L. Puts et al., JSTQE 59(3), 2023.
We are now interested to pursue the monolithic integration of RTDs with lasers and other synaptic weighting devices to form electronic-photonic neurons on chip, thereby setting the grounds for future large-scale neuromorphic circuits. The PhD positions link to a new European collaborative project SPIKEPro (Spiking Photonic-Electronic IC for Quick and Efficient Processing) within the European Innovation Council (EIC) framework. Close collaboration with the project partners, University of Strathclyde, University College London, TU Ilmenau and Hewlett-Packard Labs is foreseen.
The PhD positions
Position 1 (Focus: sensing)
This research focuses on the investigation of RTD-based neuromorphic photodetectors capable of producing threshold-based electrical spikes upon receiving low-amplitude optical stimuli. Their integration with other waveguide-based photonic components will be explored as well. This position will aim at proof-of-principle demonstration of spike-based neuromorphic sensing (e.g. event-based sensing).
Position 2 (Focus: sensing)
This research focuses on the investigation of RTD-based neuromorphic lasers capable of producing threshold-based optical spikes upon receiving low-amplitude electrical stimuli. Their integration with other waveguide-based photonic components will be explored as well. This position will aim at proof-of-principle demonstration of spike-based processing in smart sensing concepts.
Position 3 (Focus: processing)
This research focuses on the investigation of micro-disk type lasers with saturable absorbers, capable of producing low-energy spikes when receiving low-energy optical signals. Novel memristive devices for electric and photonic weighting function will be explored and co-integrated with such all-optical laser neurons. The position will aim at proof-of-concept demonstration of ultra-fast optical spike processing.
In all the positions, the work will comprise concept development, device design (incl. optical and electrical simulations), photonic chip layout, cleanroom fabrication and chip characterization in our laboratories. You will be part of the Photonic Integration (PhI) research group within the Eindhoven Hendrik Casimir Institute (EHCI). The research will be done in collaboration with European partners from academia and industry.
Specifications
- max. 38 hours per week
- Eindhoven View on Google Maps
:fill(white)/logos/tue-en-wide_acOLN2b.png)
Eindhoven University of Technology (TU/e)
Requirements
- A master's degree MSc in Electrical Engineering, Physics or Applied Physics
- A research-oriented attitude
- Ability to perform team work in an international environment
- Knowledge of the physics of optoelectronic devices
- Skills in programming
- Affinity with hands-on work in laboratory
- A systematic approach to problem solving and curiosity to understand things in-depth.
- Experience with chip characterization is desirable
- Experience with cleanroom fabrication is a plus
Conditions of employment
A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:
- Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
- Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. €2,770 max. €3,539).
- A year-end bonus of 8.3% and annual vacation pay of 8%.
- High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
- An excellent technical infrastructure, on-campus children's day care and sports facilities.
- An allowance for commuting, working from home and internet costs.
- A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.
