1

A Practical Sparse Approximation for Real Time Recurrent Learning
Recurrent neural networks are usually trained with backpropagation through time, which requires storing a complete history of network …
PDF Cite
Aligning Time Series on Incomparable Spaces
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in …
PDF Cite Code
Aligning Time Series on Incomparable Spaces
Learning Contact Dynamics using Physically Structured Neural Networks
Learning physically structured representations of dynamical systems that include contact between different objects is an important …
PDF Cite Code
Learning Contact Dynamics using Physically Structured Neural Networks
Matérn Gaussian Processes on Graphs
Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information …
PDF Cite Code
Matérn Gaussian Processes on Graphs
Could AI Democratise Education? Socio-Technical Imaginaries of an EdTech Revolution
Cite
PEEK: A Large Dataset of Learner Engagement with Educational Videos
Cite
Progress in Self-Certified Neural Networks
Cite
Semantic TrueLearn: Using Semantic Knowledge Graphs in Recommendation Systems
Cite
Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis
Probabilistic software analysis aims at quantifying the probability of a target event occurring during the execution of a program …
PDF Cite DOI
X5Learn: A Personalised Learning Companion at the Intersection of AI and HCI
Cite