excerpt shortening
This commit is contained in:
parent
eedbd2b2b5
commit
c5c70f2a7d
@ -2,7 +2,7 @@
|
|||||||
layout: single
|
layout: single
|
||||||
title: "RNN Memory Limits"
|
title: "RNN Memory Limits"
|
||||||
categories: research deep-learning recurrent-neural-networks sequence-modeling theoretical-ml
|
categories: research deep-learning recurrent-neural-networks sequence-modeling theoretical-ml
|
||||||
excerpt: "Investigated the practical limits of RNNs (vanilla, LSTM, GRU) in recalling past inputs from uncorrelated sequences via standard backpropagation."
|
excerpt: "Investigated memory limits of RNNs in recalling uncorrelated sequences."
|
||||||
header:
|
header:
|
||||||
teaser: /assets/figures/22_rnn_limits.png
|
teaser: /assets/figures/22_rnn_limits.png
|
||||||
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"
|
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"
|
||||||
|
@ -2,7 +2,7 @@
|
|||||||
layout: single
|
layout: single
|
||||||
title: "Autoencoder Trajectory Compression"
|
title: "Autoencoder Trajectory Compression"
|
||||||
categories: research deep-learning recurrent-neural-networks trajectory-analysis data-compression geoinformatics
|
categories: research deep-learning recurrent-neural-networks trajectory-analysis data-compression geoinformatics
|
||||||
excerpt: "Introduced an LSTM autoencoder approach for GPS trajectory compression, demonstrating superior reconstruction accuracy compared to Douglas-Peucker based on Fréchet distance and DTW."
|
excerpt: "LSTM autoencoder better DP for trajectory compression (Fréchet/DTW)."
|
||||||
header:
|
header:
|
||||||
teaser: /assets/figures/23_trajectory_model.png
|
teaser: /assets/figures/23_trajectory_model.png
|
||||||
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"
|
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"
|
||||||
|
Loading…
x
Reference in New Issue
Block a user