lin-shuyu

aimsMiniProject1

AttSets

AttSets in Tensorflow (IJCV 2019)

botorch

Bayesian optimization in PyTorch

floorplan

This repository contains a collection of floor plans where we will carry out experiments. The floor plan contains scale, heading away from North and wifi router positions.

GitExampleXC9

GPR-for-field-map

First AIMS mini-project

Hello-world

Just another repository. For get things started practice

ladder-latent-data-distribution-modelling

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We propose LaDDer to achieve accurate modelling of the latent data distribution in a variational autoencoder framework and to facilitate better representation learning. The central idea of LaDDer is a meta-embedding concept, which uses multiple VAE models to learn an embedding of the embeddings, forming a ladder of encodings. We use a non-parametric mixture as the hyper prior for the innermost VAE and learn all the parameters in a unified variational framework. From extensive experiments, we show that our LaDDer model is able to accurately estimate complex latent distribution and results in improvement in the representation quality.

models

Models and examples built with TensorFlow

VAE-LSTM-for-anomaly-detection

We propose a VAE-LSTM model as an unsupervised learning approach for anomaly detection in time series.

lin-shuyu/VAE-LSTM-for-anomaly-detection

We propose a VAE-LSTM model as an unsupervised learning approach for anomaly detection in time series.

lin-shuyu/ladder-latent-data-distribution-modelling

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We propose LaDDer to achieve accurate modelling of the latent data distribution in a variational autoencoder framework and to facilitate better representation learning. The central idea of LaDDer is a meta-embedding concept, which uses multiple VAE models to learn an embedding of the embeddings, forming a ladder of encodings. We use a non-parametric mixture as the hyper prior for the innermost VAE and learn all the parameters in a unified variational framework. From extensive experiments, we show that our LaDDer model is able to accurately estimate complex latent distribution and results in improvement in the representation quality.

lin-shuyu/aimsMiniProject1

lin-shuyu/AttSets

AttSets in Tensorflow (IJCV 2019)

lin-shuyu/botorch

Bayesian optimization in PyTorch

lin-shuyu/floorplan

This repository contains a collection of floor plans where we will carry out experiments. The floor plan contains scale, heading away from North and wifi router positions.

lin-shuyu/GitExampleXC9

lin-shuyu/GPR-for-field-map

First AIMS mini-project

lin-shuyu/Hello-world

Just another repository. For get things started practice

lin-shuyu/models

Models and examples built with TensorFlow

lin-shuyu/modified-wae

added my WiSE-ALE encoder-decoder architecture to WAE code

lin-shuyu/wae

Wasserstein Auto-Encoders