Posts by Collection

publications

Nonlocal Thresholds for Improving the Spatial Resolution of Pixel Detectors

Published in Journal of Instrumentation, 2019

Investigating the potential use of charge sharing between neighboring pixels in HEP sensors to increase resolution and radiation hardness.

Nachman, B. & Spies, A.F. (2019). Nonlocal Thresholds for Improving the Spatial Resolution of Pixel Detectors. Journal of Instrumentation. [BIB] [PDF]

Sparse Relational Reasoning with Object-Centric Representations

Published in ICML Dynn Workshop (Spotlight), 2022

Assessing the extent to which sparsity and structured (Obect-Centric) representations are beneficial for neural relational reasoning.

Spies, A.F., Russo, A., Shanahan, M. (2022). Sparse Relational Reasoning with Object-Centric Representations. ICML 2022 DyNN Workshop. [BIB] [PDF]

Structured World Representations in Maze-Solving Transformers

Published in NeurIPS 2023 UniReps Workshop, 2023

Transformers trained to solve mazes form linear representations of maze structure, and acquire interpretable attention heads which facilitate path-following.

Ivanitskiy, M.I.*, Spies, A.F.*, Räuker, T.* et al. Structured World Representations in Maze-Solving Transformers. NeurIPS 2023 UniReps Workshop. [BIB] [PDF]

talks

teaching

Computer Architecture

Undergraduate Course, Imperial College London, Department of Computing, 2021

Taught in lab sessions as a teaching assistant, and marked course work.

Data Structures and Algorithms

Undergraduate Course, Imperial College London, Department of Computing, 2021

Taught Imperial business students in lectures and tutorial sessions. Additionally, co-created and ran extended weekly workshop alongside Hadeel Al-Negheimish.

Maths for Machine Learning

Master's Course, Imperial College London, Department of Computing, 2021

Taught in lab sessions as a teaching assistant.

Deep Learning

Master's Course, Imperial College London, Department of Computing, 2021

Acting as a Course Support Leader, developed an autograding framework for the courseworks, combining existing departmental tools with Otter Grader to automatically mark students’ Jupyter Notebook submissions - including unit tests for various Deep Learning models. Additionally, aided with other material creation and organization, and answered many student queries.

uploads