English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The ability to recognize objects despite there being differences inappearance, known as Core Object Recognition, forms a critical part of humanperception. While it is understood that the brain accomplishes Core ObjectRecognition through feedforward, hierarchical computations through the visualstream, the underlying algorithms that allow for invariant representations toform downstream is still not well understood. (DiCarlo et al., 2012) Variouscomputational perceptual models have been built to attempt and tackle theobject identification task in an artificial perceptual setting. ArtificialNeural Networks, computational graphs consisting of weighted edges andmathematical operations at vertices, are loosely inspired by neural networks inthe brain and have proven effective at various visual perceptual tasks,including object characterization and identification. (Pinto et al., 2008)(DiCarlo et al., 2012) For many data analysis tasks, learning representationswhere each dimension is statistically independent and thus disentangled fromthe others is useful. If the underlying generative factors of the data are alsostatistically independent, Bayesian inference of latent variables can formdisentangled representations. This thesis constitutes a research projectexploring a generalization of the Variational Autoencoder (VAE), $\beta$-VAE,that aims to learn disentangled representations using variational inference.$\beta$-VAE incorporates the hyperparameter $\beta$, and enforces conditionalindependence of its bottleneck neurons, which is in general not compatible withthe statistical independence of latent variables. This text examines thisarchitecture, and provides analytical and numerical arguments, with the goal ofdemonstrating that this incompatibility leads to a non-monotonic inferenceperformance in $\beta$-VAE with a finite optimal $\beta$.

A Deeper Look at the Unsupervised Learning of Disentangled Representations in $\beta$-VAE from the Perspective of Core Object Recognition