Applied Data Science to Lower Healthcare Costs for Successful Aging
Posted by Haw-minn Lu in Machine Learning
The mission of West Health Institute is to lower healthcare costs to enable seniors to successfully age in place, with access to high-quality, affordable health and support services that preserve and protect their dignity, quality of life and independence. Data Science is fundamental …
Posted by Haw-minn Lu in Machine Learning
Metamorphic truth is a method of training an Artificial Neural Network (ANN) where the "truth" supplied during training is not fixed and may depend on the prediction made by the ANN. More specifically during training a truth metamorphism is defined as a function of the prediction …
Posted by Haw-minn Lu in Machine Learning
Quasiorthonormal encoding (QOE) is a generalization of the one-hot encoding and exploits the fact that in high dimensional vector spaces, two random vectors are almost always orthogonal. The concept originated with Kůrková and Kainen almost 25 years ago. The principle is the same as one-hot encoding when you view …
Posted by Haw-minn Lu in Machine Learning
While most popular machine learning methods such as deep learning require numerical data as input, categorical data is very common practice. For example, a person's vitals could be a combination of both, they could include height, weight (numerical) and gender, race (categorical). The challenge is to convert the categorical …
Posted by Haw-minn Lu in Machine Learning
Heat map code from https://stackoverflow.com/questions/33282368/plotting-a-2d-heatmap-with-matplotlib
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
# generate 2 2d grids for the x & y bounds
y, x = np.meshgrid(np.linspace(-3, 3, 100), np.linspace(-3, 3, 100))
z = (1 - x / 2. + x ** 5 …