Petar Velickovic

  • Citations Per Year
Learn More
In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the(More)
We propose two multimodal deep learning architectures [1] that allow for cross-modal dataflow (XFlow) between the feature extractors, thereby extracting more interpretable features and obtaining a better representation than through unimodal learning, for the same amount of training data. These models can usefully exploit correlations between audio and(More)
The Expectation Maximisation (EM) algorithm is a procedure that iteratively optimises parameters of a given model, to maximise the likelihood of observing a given (training) dataset. Assuming that our framework has unobserved data, X, observed data, Y , parameters Θ, and a likelihood function L(X,Y,Θ) = P(X,Y |Θ), we can derive the steps of the algorithm as(More)
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods’ features, we enable(More)
Antibodies play an essential role in the immune system of vertebrates and are vital tools in research and diagnostics. While hypervariable regions of antibodies, which are responsible for binding, can be readily identified from their amino acid sequence, it remains challenging to accurately pinpoint which amino acids will be in contact with the antigen (the(More)
MOTIVATION With the development of experimental methods and technology, we are able to reliably gain access to data in larger quantities, dimensions and types. This has great potential for the improvement of machine learning (as the learning algorithms have access to a larger space of information). However, conventional machine learning approaches used thus(More)
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements, derived from a dataset spanning 15000 users, collected across a range of consumergrade health devices by Nokia Digital Health Withings. We focus on predicting whether a user will successfully achieve his/her weight objective. For this, we design several deep long(More)
  • 1