16 Perowne Street
Cambridge
United Kingdom
CB1 2AY

+44 7463 757345
charlie@thehewitts.biz
chewitt.me

Charlie Hewitt

Curriculum Vitae

Profile

I'm a year old computer scientist based in the UK. I recently graduated with a master's degree in computer science from the University of Cambridge and am hoping to pursue a career in research & development. I'm particularly interested in graphics, computer vision, human-computer interaction and machine learning. A portfolio of my recent work is available at chewitt.me.

Skills

Experience

Research Associate - Computational Media Innovation Centre - 2019

Three month RA position at the CMIC, Victoria University of Wellington in New Zealand, working with researchers and industry partners to help develop innovative mixed reality technologies.

Research Intern - Microsoft Research - 2018

Six month internship at Microsoft Research in Cambridge, working with a small team to develop near-eye holographic display technologies for mixed reality.

Intern - Cydar - Summer 2017

Two month internship working at Cydar in Cambridge, helping to develop imaging technologies for surgeons to use in the OR.

Intern - Jagex Game Studios - Summer 2016

Three month internship within the web team at Jagex, focussed on projects involving the prototyping and development of potential future business opportunities.

Webmaster - Trinity Hall Boat Club - 2014-2017

Maintaining and updating the club website (trinityhallbc.co.uk), including complete website redesign, mobile compatibility update and implementation of online captaincy election system.

Treasurer - Trinity Hall June Event - 2016

Management of £150,000 budget and assistance in production of event hosting 2000 guests celebrating the end of the academic year.

Research

CNN-based Facial Affect Analysis on Mobile Devices - 2018PDF

Charlie Hewitt, Hatice Gunes

Paper focussing on the design, deployment and evaluation of Convolutional Neural Network (CNN) architectures for facial affect analysis on mobile devices. The proposed architectures equal the dataset baseline while minimising storage requirements. A user study demonstrates the feasibility of deploying the models for real-world applications.

Confidence measures for CNN classification using Gaussian processes - 2018PDF

Paper presenting a hybrid classification technique using Gaussian processes fitted on features extracted by a convolutional neural network to enable estimation of prediction confidence. The classifier is evaluated on the MNIST dataset and shown to have somewhat meaningful implications for confidence estimation.

Procedural generation of tree models for use in computer graphics - 2017PDF

Project and associated dissertation produced for part II of the Cambridge BA course evaluating the effectiveness of Lindenmeyer-Systems and a fully parametric approach in producing realistic 3D models of trees for CGI. Implemented two systems in python for use with Blender, as well as an investigation of automatic design using genetic algorithms.

Education

Trinity Hall, University of Cambridge - 2014-2018

MEng (distinction) in computer science

BA (first class) in computer science

John Hampden Grammar School - 2007-14

A Level

AS Level

Cambridge iGCSE

GCSE

Achievements / Interests

References

Dr Andreas Georgiou
Researcher
Microsoft Research
21 Station Road
Cambridge
CB1 2FB
angeor@microsoft.com
Prof. Simon Moore
Director of Studies, Computer Science
Trinity Hall
Trinity Lane
Cambridge
CB2 1TJ
simon.moore@cl.cam.ac.uk
PDF