Using two case studies (dSprites and 3dshapes), we demonstrate how CBSD can accurately detect underlying concepts that are affected by shifts and achieve higher detection accuracy compared to state-of-the-art shift detection methods.
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models.
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer.
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.
PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem.
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs.
LPGNAS learns the optimal architecture coupled with the best quantisation strategy for different components in the GNN automatically using back-propagation in a single search round.
We show that neural nets with this inductive bias achieve considerably better o. o. d generalisation performance for a range of relational reasoning tasks.
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence.
Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces).
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures.
Heuristics in theorem provers are often parameterised.
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention.