Non-autoregressive Conditional Diffusion Models for Time Series Prediction

no code implementations • 8 Jun 2023 • Lifeng Shen, James Kwok

In this paper, we propose TimeDiff, a non-autoregressive diffusion model that achieves high-quality time series prediction with the introduction of two novel conditioning mechanisms: future mixup and autoregressive initialization.

Denoising Open-Ended Question Answering +2

Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network

no code implementations • NeurIPS 2020 • Lifeng Shen, Zhuocong Li, James Kwok

This allows the temporal dynamics to be well captured by a set of multi-resolution temporal clusters.

Clustering One-Class Classification +1

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

no code implementations • 13 Nov 2017 • Qianli Ma, Lifeng Shen, Garrison W. Cottrell

As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade.

Time Series Time Series Analysis