PhD Position - Event-based Dynamics for Latent Reasoning (as part of a new MSCA Doctoral Network “ELEVATE”)

Descrizione

Testo originale dell'annuncio (in inglese)

Area of research: PHD Thesis Job description: PhD Position - Event-based Dynamics for Latent Reasoning (as part of a new MSCA Doctoral Network “ELEVATE”) The Peter Grünberg Institute - Neuromorphic Software Ecosystems (PGI-15) led by Prof. Dr. Emre Neftci explores neuromorphic computing technologies that learn and work like the brain. Our research team designs computing algorithms and architectures from the perspective of neuroscience and their physical realizations in dedicated circuits and devices. Applications of our research are targeted to improve computing in computer vision, autonomous control, data processing in mobile devices, and scientific data analysis. Your Job Latent reasoning is a versatile and powerful method for problem solving where computations are adaptively unrolled along depth at test-time. However, current models for latent reasoning are computationally expensive, memory-inefficient and difficult to train. This project will investigate principles to improve on these challenges, namely through event-driven methods and control theory for dedicated implementations of latent reasoning. These investigations will be grounded in hardware through co-design of neuromorphic hardware to improve accuracy, latency, data efficiency, and energy consumption on complex algorithmic or cognitive tasks. This project is part of the ELEVATE MSCA Doctoral Network ( https://www.elevate-dn.eu/ ) and co-supervised by our partners at the university of Liège. Your tasks in detail: Develop an event-driven learning algorithm for latent reasoning that sparsely updates network state and parameters in complex reasoning scenarios. Explore hardware realizations of the proposed latent reasoning algorithms. Quantitative comparisons with different hardware backends. Design conventional (GPU-based) deep neural networks for comparison. Publish research articles and participate in top international conferences to present your work. Complete one internship at the University of Liège and one internship at other ELEVATE partners. Participate in yearly retreats organized by the doctoral network and attend weekly meetings at PGI-15. Support the dissemination of software tools and concepts. Supervise student projects and BSc/MSc theses. Your Profile Master’s degree in physics, electrical/electronic engineering, computer science, mathematics, or a related field. Proven ability to work as part of a team and collaborate on projects. Strong coding skills for programming neural networks, machine learning theory and machine learning software frameworks (e.g., PyTorch or JAX). Curiosity-driven personality with the ability for creative and analytical thinking across discipline boundaries and abstraction levels. Knowledge of integrated circuit design and simulation using Cadence is a plus. Very good communication skills in English, both spoken and written ((at least B2/C1 level according to the CEFR: go.fzj.de/languagerequirements , ideally supported by a certificate confirming the language level). PGI-15 offers an English speaking environment, therefore German language skills are not required. Our Benefits for You We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We support you in your work with: Team & Environment: You will work in a motivated team with an international and interdisciplinary focus – at one of the largest research institutions in Europe Research & Infrastructure: You will have access to excellent scientific and technical facilities for your work Networking & Exchange: You will participate in (international) conferences and project meetings and actively build your scientific network Supervision & Support: We will accompany your doctoral studies with continuous, expert guidance from your academic supervisor Work-life balance: We offer flexible working hours to help you balance your professional and personal life. You also have the option of flexible working (in ter