I am a Machine Learning Engineer, specialising in deep learning, but my roots are in software development.
As I started in development, I have solid foundation of programming best practices and my machine learning knowledge is built on top of this, rather than the other way around.
Whilst working towards my PhD in applied deep learning, specifically object-tracking and time series analytics, I co-founded two startups from which I learned value of precise time management. I pride myself on good communication and believe a business is only as strong as its processes, especially when it comes to version control and GitOps. Though I have extensive experience in Computer Vision, Time Series Analysis, and Natural Language Processing, my interests also lie in DevOps/MLOps, and privacy-preserving AI.
Saving Our Bacon: Applications of Deep Learning in Precision Pig Farming (Computer Vision, Multi-Object Tracking, and Time Series Analysis)
Specialising in Artificial Intelligence
At Welcome, I am responsible for developing a means for mass data collection and validation through at-scale web scraping, machine learning and natural language processing (NLP). This data is then used to show people hyper-personalised places to visit near them, all of which is powered by various machine learning algorithms.
I worked on the development of a method for cancer detection using deep learning that requires only a smartphone. We localised the blood cells in an image, segmented and classified the different types of blood cells, and then determinde if there were signs of cancer.
At Fair Custodian, along with my responsibilities as Co-Founder, I headed up the research and implementation of our intellectual property. For example, using AWS Lambda for scalability and SNS/SQS for decoupled communication, I developed a pipeline to extract the key information from our customers emails using machine learning and NLPso that it could be presented to them in a concise format.
Research Analytics, an AI consultancy, was my first startup. My responsibilities ranged from business management to training and deployingmodels. One project was to design and implement a camera-basedcrowd analytics system that could track factors such as gender and ageon the edge device, whilst maintaining people’s privacy.
As a Research Technician on a large-scale project relating to the early detection of health and welfare problems in pigs, I worked with the research associates to develop a means for video data collection, storage and analysis in a remote location with minimal infrastructure.
I worked as a C# developer on an internal project designed maximise productivity and make the lives of staff as easy as possible. My primary responsibilities were implementing an effective git workflow, liaising with the team to plan new features, and ticket resolution.
At CERN, I was a developer on an open-source, digital library framework, built on Flask. I developed the disaster recovery module for the system that allowed simple destroy and restore functionality.
This implementation made use of Faster R-CNN to localise the pigs within an image. Each pig is then assigned an identity, which is tracked over time using a combination it's current trajectory and it's visual appearance using CNNs.
This work was then extended to use CNN-based re-identification methods that allowed the tracker to recover from long-term occlusions. The success of this implementation would theoretically allow the method to work across multiple cameras, however I did not have enough multi-camera data to accurately test this, which is why I focussed specifically on "tracklet stitching" (concatenating two tracked objects if they are the same identity).
I worked with a client to develop a privacy-focused crowd analytics device that estimated the age and gender of people in the vicinity of one of their advertising screens. This information was then fed back to the advertisers so they better understood the demographics of who was seeing their advertisements.
As we wanted to be as privacy conscious as possible, all of the data processing was done on the edge device (a Raspberry Pi with a camera module), meaning that we only stored the images for a fraction of a second as we processed them, and only aggregate statistics were sent to the cloud.
Reclaimer allowed users to find all the places they have accounts online and either unsubscribe from each place's marketing material, request a copy of their data or request all their data be deleted all with a single click.
Nope allowed users to generate email addresses for every site they sign up to in order to improve their privacy when signing up to new services.