Solomon Warsop

+44 7965 226707 | solomon@idenfo.com | sw@solwarsop.com | www.linkedin.com/in/solwarsop/

• A broad knowledge of mathematical concepts, statistical analysis techniques, and the scientific method; along with
• extensive Python experience (including the usage of PyTorch, TensorFlow, Vaex, Pandas, NumPy, and Flask);
• proficiency with Fortran and SQL, as well as familiarity with C++, Java, R, MATLAB, Wolfram Language, and HTML;
• deployment experience using AWS, Google Cloud, Docker, Kubernetes, and Torchserve; and
• strong skills with the Adobe Creative Suite.

Estimating full-field displacement in biological images using deep learning, Solomon J. E. T. Warsop, Soraya Caixeiro, Marcus Bischoff, Jochen Kursawe, Graham D. Bruce, and Philip Wijesinghe, (Submitted) 2024 (BIORXIV/2024/595161), https://doi.org/10.1101/2024.05.21.595161:

The estimation of full-field displacement between biological image frames or in videos is important for quantitative analyses of motion, dynamics and biophysics. However, the often weak signals, poor biological contrast and many noise processes typical to microscopy make this a formidable challenge for many contemporary methods. Here, we present a deep-learning method, termed Displacement Estimation FOR Microscopy (DEFORM-Net), that outperforms traditional digital image correlation and optical flow methods, as well as recent learned approaches, offering simultaneous high accuracy, spatial sampling and speed. DEFORM-Net is experimentally unsupervised, relying on displacement simulation based on a random fractal Perlin-noise process and optimised training loss functions, without the need for experimental ground truth. We demonstrate its performance on real biological videos of beating neonatal mouse cardiomyocytes and pulsed contractions in Drosophila pupae, and in various microscopy modalities. We provide DEFORM-Net as open source, including inference in the ImageJ/FIJI platform, for rapid evaluation, which will empower new quantitative applications in biology and medicine.

Innovation Specialist - AI & Machine Learning, Idenfo, London, England, 2022-Present:

• Currently, I research and develop applications of artificial intelligence and machine learning for identity verification, such as facial comparison, anti-spoofing, and forgery detection. This includes leading end-to-end development of deep neural networks: managing data collection, iterating on model designs, evaluating performance, and deploying for production.
• For example, I have personally developed a facial comparison model from scratch, which achieved 99.7% accuracy (with a false positive rate < 1 x 10^-4 %) on a large and diverse representative dataset. Now integrated into our identity verification platform, this model is soon to be used in production to verify customer identities for Pakistan's largest microfinance bank.
• I also work on improving public domain name screening systems through the integration of entity extraction, sentiment analysis, and other natural language processing techniques.
• In addition to my machine learning research, I have led data analysis on several on-site anti-money-laundering system tuning projects at Dubai-based banks. This involved the analysis of large financial datasets (>100M transactions) as well as the development of rule logic simulations and visualisation tools. Above-the-line and below-the-line testing methods were utilised to fine-tune existing rules, then modifications to the rule logic were proposed after examining transaction distributions and typical customer behaviour. The efficacy of newly implemented rules was estimated through backtesting.

Mathematics and Science Tutor, Freelance, Frome, England, 2019.

Intern, Centre for the Analysis of Motion, Entertainment Research and Applications, Bath, England, 2017:

• I processed data from optical motion capture systems.

Assistant Database Administrator, Kensington Domestic Appliances, Heathfield, England, 2015-16:

• I managed the database supporting the online store.

Master's in Physics (First-class, Integrated), University of St Andrews, Scotland, 2018-22:

• I completed a research-based Master's project, "Measuring biomechanics with deep learning", during which I:
• developed convolutional neural networks for measuring displacements within bright-field microscopy images of live biological samples;
• created a synthetic dataset and used it to train networks that were able to achieve greater accuracy than all available alternative methods, as well as providing significant reductions in computation time; and
• performed exploratory work, investigating the potential of unsupervised and semi-supervised learning techniques using an adversarial network.
• The work performed during this project formed the basis of the publication "Estimating full-field displacement in biological images using deep learning" (BIORXIV/2024/595161).
• I studied a wide range of topics across Physics, Astronomy, and Mathematics, including:
• quantum field theory;
• Monte Carlo simulation;
• magnetohydrodynamics;
• computational astrophysics;
• electronics; and
• signal processing.
• I was named on the Dean's List (for averaging first-class results across all modules) in every academic year.
• I was awarded:
• the Astronomy and Astrophysics Medal for the highest academic performance during Junior Honours;
• the Physics Medal for the highest academic performance during my final year; and
• the MPhys Project Prize for the year's best Master's project.

A Levels, Frome Community College, 2016-18:

• I studied Physics (A*), Mathematics (A*), Chemistry (A), and Photography (A*): the highest results in the year group.