Occlusion Based Explanations of Black-Box Models for Deep Learning

Occlusion sensitivity analysis allows us to better understand trained machine learning models by identifying which parts of a given input are most salient in determining the model’s prediction. It is particularly valuable as it can be applied to black-box models i.e. models with internal representations which are difficult to access or interpret.   Occlusion sensitivity […]

Continue reading

StackOverflow Sidekick

StackOverflow as an active question and answer community of people with an interest in programming. For many programmers, it is an invaluable resource that provides candidate solutions for the myriad small and large problems that programming tasks can bring with them. Unfortunately, most users of StackOverflow are merely passive consumers of the content on the […]

Continue reading

Creative Autonomous Navigation and Learning by Mobile Robots in Unstructured Public Spaces

Mobile robots have had highly controlled structural constraints on route planning and execution. Some mobile hospital robots run on clearly marked permanent tracks in public corridors for example. Safety considerations naturally motivate such constraints. As mobile robots become more integrated into society as autonomous entities, more ambitious robot navigation in public spaces is being attempted. […]

Continue reading

Annotation of 3D models

An existing tool annotates 3D models with polygons and labels. It makes use of the LibGDX Java library, which was designed for computer games. The 3D models that we are using, of Ancient Egyptian coffins, are becoming too big however to be handled by this library. The task would be to redesign the tool, but […]

Continue reading

A strategy video-game for collaborative agents with a personality

In this project we aim to develop a multiagent system to play a strategy video game [1].  The basic idea is that a group of agents acting on behalf of the player work collaboratively to achieve a common goal. At each step a decision is to be made for which action the group should take. […]

Continue reading

Improved Tracing and Profiling for the GAP language

GAP is an interpreted dynamic language, similar to Python, designed for mathematics and combinatorics, in particular problems involving groups and semigroups.   GAP has a simple profiler, which records which lines of a file are executed, and how long each takes. This information is used to show users where their program is spending the most […]

Continue reading

Automated Creation of games with A.I.

This proposal aims to automatically generate levels of games, and measuring the difficulty of the resulting levels. Abstract There is a history of generating puzzles using A.I., from Chess problems to Infinite runner games. Recently there has been progress in generating levels, and also measuring the difficulty of these levels, for a human player. This […]

Continue reading

The City and the Writer: Facilitating the Analysis of the Works by Ramón Gómez de la Serna

Spanish writer Ramón Gómez de la Serna (1888-1963) is the best-known avant-garde writer of Spanish 20th century literature, comparable to James Joyce or Marcel Proust. An extraordinarily prolific writer, his complete works reach more than 20.000 pages (including novels, essays, plays, and collections of maxims), and yet, a big amount of his writings, those published […]

Continue reading

Learning to shift in a dynamic environment

For a robot to autonomously and freely move in spaces where people and other robots are moving, these other entities have to be navigated safely. Moving entities are recognised to be a more challenging problem than static ones due to motion planning requiring variable trajectories in space-time rather than just paths in space to be […]

Continue reading

Enabling NAO robots to learn (Nao programming)

The NAO humanoid robot [1] is a high-end robot (about the size of a small child) used in education and research and also other areas such as banking. It offers opportunities to explore areas such as 3-D imaging, speech recognition and production, vision processing, face tracking, complex limb motions, and artificially intelligent and emotional interaction. The […]

Continue reading