Autoencoders and Embeddings: How Unsupervised Structural Learning Enables Fast and Efficient Goal-Directed Learning

Nandigam, Sridhar; Tabashum, Thasina; Xiao, Ting

doi:10.1007/978-3-030-84729-6_3

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al proposed a convolutional neural network and predicted an expanded disability status scale (EDSS) to measure the severity of multiple sclerosis [ 9 ]. In particular, as an unsupervised machine learning method, deep autoencoders use deep neural networks to encode data into a reduced representation and then evaluate the quality of that encoding by reconstructing the original data [ 10 ]. Such reduced encodings provide a valuable, succinct summary of the often highly correlated and noisy original dataset.…”

Section: Introductionmentioning

confidence: 99%

Autoencoder Composite Scoring to Evaluate Prosthetic Performance in Individuals with Lower Limb Amputation

et al. 2022

View full text Add to dashboard Cite

We created an overall assessment metric using a deep learning autoencoder to directly compare clinical outcomes in a comparison of lower limb amputees using two different prosthetic devices—a mechanical knee and a microprocessor-controlled knee. Eight clinical outcomes were distilled into a single metric using a seven-layer deep autoencoder, with the developed metric compared to similar results from principal component analysis (PCA). The proposed methods were used on data collected from ten participants with a dysvascular transfemoral amputation recruited for a prosthetics research study. This single summary metric permitted a cross-validated reconstruction of all eight scores, accounting for 83.29% of the variance. The derived score is also linked to the overall functional ability in this limited trial population, as improvements in each base clinical score led to increases in this developed metric. There was a highly significant increase in this autoencoder-based metric when the subjects used the microprocessor-controlled knee (p < 0.001, repeated measures ANOVA). A traditional PCA metric led to a similar interpretation but captured only 67.3% of the variance. The autoencoder composite score represents a single-valued, succinct summary that can be useful for the holistic assessment of highly variable, individual scores in limited clinical datasets.

show abstract

Section: Introductionmentioning

confidence: 99%