Name: HongminWu
Type: User
Company: Guangdong University of Technology
Bio: I am a Ph.D. student at the Guangdong University of Technology.
Major in Nonparametric Bayesian Method, Anomaly Detection/Classification, Motion Planning
Location: Guangdong University of Technology, China
HongminWu's Projects
Stable Estimation of Dynamical System for Skill Learning and Realtime Collision Avoidance
Reinforcement Learning with Deep Energy-Based Policies
Sticky hierarchical Dirichlet process hidden Markov model for time series denoising
Official code for "Task-Embedded Control Networks for Few-Shot Imitation Learning".
A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.
Time series classification and clustering code written in Python. Mostly based on the work of Dr. Eamonn Keogh at University of California Riverside
the state-of-the-art repo for time_series_anomaly_detection_classification_clustering
Automatic extraction of relevant features from time series:
UCI-RobotExecutionFaliuresDataSet for testing the anomaly classification
Code for unsupervised online learning (reaching prediction)
Lstm variational auto-encoder API for time series anomaly detection and features extraction
VRAE Variational Recurrent Autoencoder
Variational Autoencoder for Dimensionality Reduction of Time-Series
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
A little word cloud generator in Python