Kevin Chen (Kevin-Chen0)

Kevin-Chen0

Geek Repo

Location:Washington D.C.

Twitter:@kevrchen

Github PK Tool:Github PK Tool

Kevin Chen's repositories

dnn-time-series

End-to-end deep learning predictive modeling package for time-series data.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:8Issues:2Issues:0

pyota-api

Developing applications on top of IOTA Tangle made easy! Using Python (pyota).

Language:PythonStargazers:2Issues:2Issues:0

py-postgresql

Pipeline between Python ETL code and PostgreSQL data queries.

Language:PythonStargazers:1Issues:2Issues:0
Language:PythonStargazers:0Issues:1Issues:0

Coupled-VAE-Improved-Robustness-and-Accuracy-of-a-Variational-Autoencoder

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs the outliers with a higher penalty by generalizing the original loss function to the coupled entropy function, using the principles of nonlinear statistical coupling. We evaluate the performance of the coupled VAE model using the MNIST dataset. Compared with the traditional VAE algorithm, the output images generated by the coupled VAE method are clearer and less blurry. The visualization of the input images embedded in 2D latent variable space provides a deeper insight into the structure of new model with coupled loss function: the latent variable has a smaller deviation and the output values are generated by a more compact latent space. We analyze the histograms of probabilities for the input images using the generalized mean metrics, in which increased geometric mean illustrates that the average likelihood of input data is improved. Increases in the -2/3 mean, which is sensitive to outliers, indicates improved robustness. The decisiveness, measured by the arithmetic mean of the likelihoods, is unchanged and -2/3 mean shows that the new model has better robustness.

Language:PythonStargazers:0Issues:1Issues:0

deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0
Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:1Issues:0
License:BSD-3-ClauseStargazers:0Issues:2Issues:0

google-research

Google Research

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:0Issues:1Issues:0

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Language:PythonLicense:NOASSERTIONStargazers:0Issues:2Issues:0

image-classification-cnn

A Udacity Machine Learning Engineer (MLE) Nanodegree project where I classify images of dogs and even humans and objects into types of dog breed based on resemblance using Convolutional Neural Networks (CNNs).

Stargazers:0Issues:2Issues:0

Machine-Learning-for-Algorithmic-Trading-Second-Edition

Code and resources for Machine Learning for Algorithmic Trading, 2nd edition.

Language:Jupyter NotebookStargazers:0Issues:1Issues:0

machine-learning-with-minishift

Training and Deploying Machine Learning Models with Containers

Language:HTMLStargazers:0Issues:1Issues:0

neural_prophet

NeuralProphet: A simple forecasting package

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

pommerman-playground

PlayGround: AI Research into Multi-Agent Learning.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

RL-Quadcopter-2

Teach a Quadcopter How to Fly!

Language:Jupyter NotebookStargazers:0Issues:2Issues:0

udacity-mle-nd

My Udacity Machine Learning Engineer (MLE) Nanodegree projects.

Language:Jupyter NotebookStargazers:0Issues:2Issues:0