excerpt shortening

This commit is contained in:
Steffen Illium 2025-03-31 20:28:14 +02:00
parent eedbd2b2b5
commit c5c70f2a7d
2 changed files with 2 additions and 2 deletions

View File

@ -2,7 +2,7 @@
layout: single
title: "RNN Memory Limits"
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:
teaser: /assets/figures/22_rnn_limits.png
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"

View File

@ -2,7 +2,7 @@
layout: single
title: "Autoencoder Trajectory Compression"
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:
teaser: /assets/figures/23_trajectory_model.png
scholar_link: "https://scholar.google.de/citations?user=NODAd94AAAAJ&hl=en"