CMOS and beyond CMOS
Discover why imec is the premier R&D center for advanced logic & memory devices. anced logic & memory devices.
Connected health solutions
Explore the technologies that will power tomorrow’s wearable, implantable, ingestible and non-contact devices.
Life sciences
See how imec brings the power of chip technology to the world of healthcare.
Sensor solutions for IoT
Dive into innovative solutions for sensor networks, high speed networks and sensor technologies.
Artificial intelligence
Explore the possibilities and technologies of AI.
More expertises
Discover all our expertises.
Research
Be the first to reap the benefits of imec’s research by joining one of our programs or starting an exclusive bilateral collaboration.
Development
Build on our expertise for the design, prototyping and low-volume manufacturing of your innovative nanotech components and products.
Solutions
Use one of imec’s mature technologies for groundbreaking applications across a multitude of industries such as healthcare, agriculture and Industry 4.0.
Venturing and startups
Kick-start your business. Launch or expand your tech company by drawing on the funds and knowhow of imec’s ecosystem of tailored venturing support.
/Job opportunities/Deep learning on analog accelerators with novel memory technology

Deep learning on analog accelerators with novel memory technology

PhD - Leuven | More than two weeks ago

Enable disruptive computing for AI with novel memory technology
Imec is a world-leading research and innovation hub in nanoelectronics and digital technologies. The machine learning program at Imec is leading the quest for computationally- and energy-efficient machine learning accelerators.  By leveraging its memory technology, Imec aims to develop analog in memory computing (AiMC) solutions built on emerging non-volatile memory devices. These devices can mitigate the challenges related to learning algorithms, by performing the computations in the memory itself. Compared to classical Von Neumann architectures, in which computations are performed on a central processor after memory elements have been fetched from outside, compute-in-memory approaches have the promise to increase energy efficiency by orders of magnitudes, while at the same time allowing for the required high throughput. Imec‘s machine learning research is driving the co-evolution of hardware and algorithms needed to facilitate the move to this new computational paradigm

Analog In Memory Computing has established itself as an energy efficient candidate for a wide range of Deep Learning Inference hardware. Current research shows the limitations of devices to be used for neural network inference and training due to several non-idealities. This PhD topic will focus on algorithms to enable analog computing based on novel memory technology for deep learning. The approach adopted for such a system would require co-optimization at every abstraction level of a computing system, starting from algorithm, architecture, circuits to device engineering.

Imec has a research program on developing new algorithms, systems and devices for deep learning. The PhD topic will enable the long-term vision of this research program to define and engineer algorithms and memory devices apt for Deep Learning. The student will be supported and supervised by a group of researchers working on enabling disruptive technology solution in the AI domain.

This PhD will build on imec's experience of combining system level constraints for technology or semiconductor innovation. The student will focus on the STCO techniques to identify, explore and solve the bottlenecks of engineering algorithms and devices for Analog-In-Memory-Compute systems. The research will involve fundamental breakthrough in algorithm level techniques coupled with novel circuit and device technology to find an energy efficient solution for running deep learning algorithms. This topic would be classic example of System-Technology-Co-Optimization philosophy pursued in imec.

Required background: fundamental knowledge in neural networks, device physics, basic computer architecture, basic circuit design skills would be preferred but not mandatory



Required background: Electrical Engineering, Nanotechnology, Computer Science

Type of work: 60% algorithm development and device modeling, 20% experimental, 10% literature

Supervisor: Ingrid De Wolf

Co-supervisor: Peter Vrancx

Daily advisor: Arindam Mallik, Jonas Doevenspeck

The reference code for this position is 2021-064. Mention this reference code on your application form.

This website uses cookies for analytics purposes only without any commercial intent. Find out more here. Our privacy statement can be found here. Some content (videos, iframes, forms,...) on this website will only appear when you have accepted the cookies.