New opportunity: AstraZeneca to fund Compass PhD project

Novel semi-supervised Bayesian learning to rapidly screen new oligonucleotide drugs for impurities.

This is an exciting opportunity to join Compass’ 4-year programme with integrated training in the statistical and computational techniques of Data Science. You will be part of a dynamic cohort of PhD researchers hosted in the historic Fry Building, which has recently undergone a £35 million refurbishment as the new home for Bristol’s School of Mathematics.

This fully-funded 4 year studentship covers:

  • tuition fees at UK rate
  • tax-free stipend of up £19,609 per year for living expenses and
  • equipment and travel allowance to support research related activities.

This opportunity is open to UK, EU, and international students.  (more…)

Launch of industry-focused seminar series DataScience@Work

Compass is excited to announce the launch of the DataScience@work seminar series. This new seminar series invites speakers from external organisations to talk about their experiences as Data Scientists in industry, government and the third sector. The dual meaning of DataScience@work focuses talks on both the technical side of the speakers’ roles as well as working as part of a wider organisation, and building a career in data science.

Highlighting the importance of the new seminar series, Prof Nick Whiteley (Compass Director) says…

Prof Nick Whiteley addresses industry partners

Compass aims to develop scientific and professionally agility in its students. Our goal is to connect technical expertise in data science with experience of thinking, communicating and collaborating across disciplines and across sectors. In our new DataScience@Work seminar series, Compass partners from industry will share insights into the key role of Data Science within their organisations, their objectives and future outlook. This is a great opportunity for our students to learn about career trajectories beyond academia, helping shape their aspirations and personal goals for life beyond the PhD. I’m especially grateful to Adarga, CheckRisk, IBM Research, Improbable, and Shell for leading this first season of DataScience@Work and for their ongoing support for Compass.

Invited speakers to the 2020/21 session include:

 

Compass Special Lecture: Jonty Rougier

Compass is excited to announce that Jonty Rougier (2021 recipient of the Barnett Award) will be delivering a Compass Special Lecture.

Jonty’s experience lies in Computer Experiments, computational statistics and Machine Learning, uncertainty and risk assessment, and decision support. In 2021, he was awarded Barnett Award by the RSS, which is made to those internationally recognised for contributions in the field of environmental statistics, risk and uncertainty quantification. Rougier has also advised several UK Government departments and agencies, including a secondment to the Cabinet Office in 2016/17 to contribute to the UK National Risk Assessment.

 

Student Perspectives: LV Datathon – Insurance Claim Prediction

A post by Doug Corbin, PhD student on the Compass programme.

In a recent bout of friendly competition, students from the Compass and Interactive AI CDT’s were divided into eight teams to take part in a two week Datathon, hosted by insurance provider LV. A Datathon is a short, intensive competition, posing a data-driven challenge to the teams. The challenge was to construct the best predictive model for (the size of) insurance claims, using an anonymised, artificial data set generously provided by LV. Each team’s solution was given three important criteria, on which their solutions would be judged:

  • Accuracy – How well the solution performs at predicting insurance claims.
  • Explainability – The ability to understand and explain how the solution calculates its predictions; It is important to be able to explain to a customers how their quote has been calculated.
  • Creativity – The solution’s incorporation of new and unique ideas.

Students were given the opportunity to put their experience in Data Science and Artificial Intelligence to the test on something resembling real life data, forming cross-CDT relationships in the process.

Data and Modelling

Before training a machine learning model, the data must first be processed into a numerical format. To achieve this, most teams transformed categorical features into a series of 0’s and 1’s (representing the value of the category), using a well known process called one-hot encoding. Others recognised that certain features had a natural order to them, and opted to map them to integers corresponding to their ordered position. (more…)

New opportunity: a jointly funded studentship with FAI Farms

Compass is very excited to advertise this PhD studentship in collaboration with FAI Farms on a vision-based system for automated poultry welfare assessment through deep learning and Bayesian modelling.

About the Project

This is an exciting opportunity to join Compass’ 4-year programme with integrated training in the statistical and computational techniques of Data Science. You will be part of a dynamic cohort of PhD researchers hosted in the historic Fry Building, which has recently undergone a £35 million refurbishment as the new home for Bristol’s School of Mathematics.

FAI Farms

FAI Farms is a multi-disciplinary team working in partnership with farmers and food companies to provide practical solutions for climate and food security. FAI’s state-of-the-art strategic advice, data insight, and education services, are powered by science, technology and best practice. Our strategic and evidence-based approach is focused on driving meaningful improvements across supply chains, mitigating risks and realising long term business benefits for our partners.

The aim of this PhD project is to create a vision-based system for the automated assessment of chicken welfare for use in poultry farms. The welfare of broiler chickens is a key ethical and economic challenge for the sustainability of chicken meat production. The presentation of natural, positive behaviour is important to ensure a “good life” for livestock species as well as being an expectation for many consumers. At present there are no ways to measure this, with good welfare habitually defined as the absence of negative experience. In addition, automated tracking of individual birds is very challenging due to occlusion and complexity. In this project the student will instead harness and develop novel deep learning approaches that consider individual animals and their behaviours probabilistically within the context of local and general activity within the barn and wider flock. The inferred behaviour rates amongst the flock will then be integrated with on-farm production, health and environmental data through Bayesian time series modelling to identify risk factors for positive welfare, predict farms at risk of poor welfare, and suggest interventions that avoid this scenario.

(more…)

Skip to toolbar