Martin Ferianc

Martin Ferianc

AI Research Engineer

Helsing

About

Martin is an AI Research Engineer at Helsing, London, UK. Martin obtained a PhD in Electronic and Electrical Engineering from University College London, London, UK in 2024. Prior to that, Martin obtained an MEng in Electronic and Information Engineering from Imperial College London, London, UK in 2015. His research interests include Bayesian neural networks, deep learning , hardware acceleration and confidence calibration. He has hands-on experience from industrial/academic placements in different countries.

Download my resumé/CV.

Interests
  • Machine Learning
  • Uncertainty Quantification
  • Hardware Optimisation
  • Real-world Deployment of Machine Learning Systems
  • Edge AI
  • Computer Vision
  • Confidence Calibration
Education
  • PhD in Electornic and Electrical Engineering, 2019-2024

    University College London

  • MEng in Electronic and Information Engineering, 2015-2019

    Imperial College London

Industrial Experience

 
 
 
 
 
AI Research Engineer
Sep 2024 – Present London, United Kingdom
Verification, validation, assurance and confidence quantification and calibration of machine learning models
 
 
 
 
 
Machine Learning Consultant
Oct 2023 – Jan 2024 London, United Kingdom
Designed and delivered a learnable recommendation system for a customer and business-agnostic discount optimisation
 
 
 
 
 
Applied Science Research Intern
Jul 2022 – Nov 2022 Berlin, Germany
Continual learning, in the domain of computer vision and natural language processing, to reduce resource costs in model retraining on new data
 
 
 
 
 
Research Scientist Intern
Jul 2021 – Nov 2021 Montreal, Quebec, Canada
Structured neural network compression for real-world deployment on embedded devices for computer vision applications through causal inference
 
 
 
 
 
Machine Learning Consultant
Jun 2020 – Jun 2020 London, United Kingdom
Delivered an end-to-end machine learning pipeline for CT scans segmentation to an industrial healthcare client
 
 
 
 
 
Machine Learning/AI Advisor
Nov 2019 – Jan 2021 London/Bratislava, United Kingdom/Slovakia
Advising and evaluating implementations of time-series data classification and regression from medical records
 
 
 
 
 
Machine Learning Researcher
Jul 2020 – Oct 2020 (Virtual) Cambridge, United Kingdom
Investigation into combining variational inference with quantisation for hardware-efficient Bayesian neural networks
 
 
 
 
 
AI Toolchain Researcher
Apr 2018 – Oct 2018 Shenzhen/London, China/United Kingdom
Developed a verification platform for hardware implementation of convolutional neural networks on FPGAs
 
 
 
 
 
Software Engineer & Consultant Summer Intern
Jul 2016 – Sep 2016 Bratislava, Slovakia
Automated processing of data from smart-electrometers into SAP systems that improved the initially manual processing time from hours to seconds

Teaching/Service

  • Teaching

    • Teaching Assistant in Integrated Machine Learning Systems: Emerging Topics at UCL, Department of Electronic and Electrical Engineering

    • Co-Lecturer in Foundations of Machine Learning and Data Science at UCL, Department of Information Studies

    • Co-Lecturer in Introduction to Machine Learning, a Masterclass at UCL, Department of Pharmacology

      • Spring 2020
    • Teaching Assistant at the Defence Science and Technology Laboratory, on behalf of UCL and the Alan Turing Institute

      • February 2020/November 2020
    • Teaching assistant at OxML Summer school

      • Summer 2020
    • Postgraduate Teaching Assistant for Introduction to Machine Learning at UCL, Department of Information Studies

    • Postgraduate Teaching Assistant for Programming 2 at UCL, Department of Information Studies

    • Undergraduate Teaching Assistant for Introduction to Computer Architecture at Imperial College London, Department of Electrical and Electronic Engineering

      • Autumn 2017/Autumn 2018: link
    • Teaching assistant at PAPAA Summer School

      • Summer 2018
  • Service

    • Reviewer:

      • Journals:
        • IEEE Transactions for Neural Networks and Learning Systems (TNNLS)
        • IEEE Journal of Selected Topics in Signal Processing (JSTSP)
        • IEEE Transactions on Circuits and Systems I (TCAS-I)
        • IEEE Transactions on Image Processing (TIP)
        • IEEE Solid-State Circuits Letters (SSC-L)
        • IEEE Transactions on Computers (TC)
        • IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)
        • IEEE Transactions on Circuits and Systems for Artificial Intelligence (TCASAI)
        • Transactions on Machine Learning Research (TMLR)
        • PLOS ONE
      • Conferences/Workshops:
        • AISTATS 2024
        • UAI 2024
        • IEEE Mediterranean Conference on Control and Automation 2023 (MED)
        • Efficient Deep Learning for Computer Vision (CVPR Workshop) 2023
        • Workshop on Structured Probabilistic Inference & Generative Modeling (ICML Workshop) 2023
        • Workshop on Spurious Correlations, Invariance, and Stability (ICML Workshop) 2023
        • Workshop on Causal Representation Learning (NeurIPS Workshop) 2023
        • IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip 2023
        • International Conference on Artificial Neural Networks 2023/22/21 (ICANN)
    • Mentor:

      • Growni: Remote counselling to self-driven high-school students from university alumni
    • Organiser:

      • Weekly Machine learning reading group at UCL EE Department (~25 people) 2023

Accomplishments

Awards and Honours

  • 2017

    • 2017 Faculty of Engineering Undergraduate Research Opportunities Programme Award, Imperial College London

    • 2017 Študenti do sveta Scholarship

    • 2017 Forbes Slovakia 30 under 30

  • 2016

    • 2016 Winners of PA Consulting Group Video Challenge

    • 2016 Finalists of Social Impact Award

    • 2016 Finalists of HSBC Grow Your Future

    • 2016 First prize at 2016 CISCO Switch-up Challenge

  • 2015

    • 2015 National Representative at Expo in Milan, Italy

    • 2015 Third place at Unilever Sustainability Challenge

  • 2014

    • 2014 Diploma of St. Gorazd

    • 2014 National Representative at Expo Sciences Europe

    • 2014 Gold Medal and a Special Award at I-SWEEEP

    • 2014 Ambassador of Youth

    • 2014 Award of the Rector of Paneuropean University in Bratislava

    • 2014 Stredoškoláci do sveta Scholarship

    • 2014 Green Fond Project Grant

  • 2013

    • 2013 Award of the Comenius University for the Best Science Project

    • 2013 Diploma of St. Gorazd

    • 2013 Silver medal at the Austrian Young Physicist Tournament

    • 2013 Third place at CEMACH

Media appearances

Publications

Quickly discover relevant content by filtering publications.
(2024). Smart Laser Sintering: Deep Learning-Powered Powder Bed Fusion 3D Printing in Precision Medicine. International Journal of Pharmaceutics.

PDF Cite

(2024). Learning-based MPC with uncertainty estimation for resilient microgrid energy management. 2024 IFAC Safeprocess.

PDF Cite

(2024). Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks. Transactions on Machine Learning Research.

PDF Cite Code

(2023). An Online Learning Method for Microgrid Energy Management Control. 2023 31st Mediterranean Conference on Control and Automation (MED).

PDF Cite

(2023). Impact of Noise on Calibration and Generalisation of Neural Networks. ICML 2023 Workshop on Spurious Correlations, Invariance, and Stability.

PDF Cite

(2023). MIMMO: Multi-Input Massive Multi-Output Neural Network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

PDF Cite

(2023). Renate: A library for real-world continual learning. 2023 Continual Learning in Computer Vision (CLCV) workshop at CVPR 2023.

PDF Cite

(2022). Simple Regularisation for Uncertainty-Aware Knowledge Distillation. ICML 2022 Workshop on Distribution-Free Uncertainty Quantification.

PDF Cite Code

(2022). Accelerating Bayesian Neural Networks via Algorithmic and Hardware Optimizations. IEEE Transactions on Parallel and Distributed Systems.

PDF Cite DOI

(2022). FPGA-based Acceleration for Bayesian Convolutional Neural Networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

PDF Cite DOI

(2022). Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator. 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC).

PDF Cite DOI

(2022). Enabling fast uncertainty estimation: accelerating bayesian transformers via algorithmic and hardware optimizations. Proceedings of the 59th ACM/IEEE Design Automation Conference.

PDF Cite

(2021). Optimizing Bayesian Recurrent Neural Networks on an FPGA-based Accelerator. 2021 International Conference on Field-Programmable Technology (ICFPT).

PDF Cite DOI

(2021). High-Performance FPGA-based Accelerator for Bayesian Neural Networks. 2021 58th ACM/IEEE Design Automation Conference (DAC).

PDF Cite DOI

(2021). Toward Full-Stack Acceleration of Deep Convolutional Neural Networks on FPGAs. IEEE Transactions on Neural Networks and Learning Systems.

PDF Cite DOI

(2021). ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation. Artificial Neural Networks and Machine Learning – ICANN 2021.

PDF Cite Code

(2021). Improving Performance Estimation for Design Space Exploration for Convolutional Neural Network Accelerators. Electronics.

PDF Cite Code

(2021). On Causal Inference for Data-free Structured Pruning. The AAAI-22 Workshop on Information-Theoretic Methods for Causal Inference and Discovery.

PDF Cite

(2021). On the effects of quantisation on model uncertainty in Bayesian neural networks. Uncertainty in Artificial Intelligence.

PDF Cite Code

(2021). VINNAS: Variational Inference-based Neural Network Architecture Search. arXiv pre-print.

PDF Cite

(2020). Optimizing FPGA-Based CNN Accelerator Using Differentiable Neural Architecture Search. 2020 IEEE 38th International Conference on Computer Design (ICCD).

PDF Cite DOI

(2020). Improving Performance Estimation for FPGA-Based Accelerators for Convolutional Neural Networks. Applied Reconfigurable Computing. Architectures, Tools, and Applications.

PDF Cite Code

(2019). Static Block Floating-Point Quantization for Convolutional Neural Networks on FPGA. 2019 International Conference on Field-Programmable Technology (ICFPT).

PDF Cite DOI

(2019). F-E3D: FPGA-based Acceleration of an Efficient 3D Convolutional Neural Network for Human Action Recognition. 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP).

PDF Cite DOI

(2018). A Real-Time Object Detection Accelerator with Compressed SSDLite on FPGA. 2018 International Conference on Field-Programmable Technology (FPT).

PDF Cite DOI

Open Source Projects

  • YAMLE - Creator

    • YAMLE: Yet Another Machine Learning Environment facilitates rapid prototyping and experimentation with machine learning models and methods

  • Renate - Founding Contributor

    • Continual learning with hyperparameter tuning, model selection after each update, and a variety of continual learning strategies

  • OL-EMS - Founding Contributor

    • Online learning control algorithms specialising in energy management systems

Contact