David Rawlinson


Experiment/Theory

Understanding Equivariance

Posted by David Rawlinson on
Understanding Equivariance

Effect of univariate perturbation of hidden layer resulting from Predictive Capsules algorithm

We are exploring the nature of equivariance, a concept that is now closely associated with the capsules network architecture (see key papers Sabour et al, and Hinton et al). Machine learning representations that capture equivariance must learn the way that patterns in the input vary together, in a ...

Experiment

Sparse Unsupervised Capsules Generalize Better

Posted by David Rawlinson on
Sparse Unsupervised Capsules Generalize Better

Equivariances discovered by the Sparse Unsupervised Capsules algorithm variant

We've just uploaded a spin-off research paper to arXiv titled "Sparse Unsupervised Capsules Generalize Better". So what's it all about? Capsules Networks You may have heard of Capsules Networks already - if not, have a read of one of these blog articles (here, here, here, or here (EM routing)), ...

General

AGI Conference 2017

Posted by David Rawlinson on

We attended the 2017 10th Conference on Artificial General Intelligence, which was located in our hometown of Melbourne, Australia! Excitingly, the IJCAI 2017 conference is also in Melbourne this week and ICML 2017 was in Sydney this year. In particular, the "Architectures for Generality and Au ...

Experiment

Region-Layer Experiments

Posted by David Rawlinson on
Region-Layer Experiments

Typical results from our experiments: Some active cells in layer 3 of a 3 layer network, transformed back into the input pixels they represent. The red pixels are positive weights and the blue pixels are negative weights; absence of colour indicates neutral weighting (ambiguity). The w ...