Home

Locally linear embedding

LLE is an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs. Steps select neighbors \[\boldsymbol{X}_m = \sum_{i\in S_m} W_{mi} \boldsymbol{X}_i\] reconstruct with weights \[\mathcal{F} = \sum^N_{m=1} \| \boldsymbol{X}_m-\sum^N_{i=1} W_{mi} \boldsymb...

Read more