Uncategorized

KNIME – Machine Learning Approach – Classification

It's the standard process everywhere for Machine Learning, aptly summarized in the flowchart below. This is probably one of the simplest depictions you will come across anywhere. A detailed look into the steps from KNIME angle: Load your input dataUnderstand what's in it: Number of Rows and Columns, and Datatypes. Notice these two columns. ?… Continue reading KNIME – Machine Learning Approach – Classification

Data Analysis, Data Visualization

KNIME Analytics Platform – Visualizations

When you have 3700 nodes, you are bound to have some visualizations in it. You would notice them under Views > Local. Histogram: Columns to display at right bottom and binning variable in the dropdown. There are more options in visualization pane itself - selections, grouping criteria and all. Because there are always multiple records… Continue reading KNIME Analytics Platform – Visualizations

AI Ethics

Fairness in AI – How Mature are We to Introduce it?

Fairness in AI is some topic which is gaining pace very fast. Looking at it holistically, we don't have a proper definition for Fairness in AI. What is fairness? Something which ensures that there is no bias. The bias can be racial, the bias can be economic, can be age related or can be anything.How… Continue reading Fairness in AI – How Mature are We to Introduce it?

Image Processing, Machine Learning

OpenCV + Posenet + Mobilenet – A Simple Implementation

Openpose is a good model for pose estimation but, it's comparatively slow and more taxing on the system. Well, there is a faster, smaller(but more error prone) human pose estimation based on mobilenet which uses the first 19 elements as against the usual full set. The model is some 7.5 MB as against the standard… Continue reading OpenCV + Posenet + Mobilenet – A Simple Implementation