- Calculate prediction (y) & cost using a single datapoint
- Using a variety of datapoints generalizes our model, i.e., it learns W, b values that can be used to predict any feature value.
- For simplicity, we use least minimum squared error (MSE) as our cost function.
- Create a TF Graph with model & cost, and initialize W, b with some values
- We select a datapoint (x, y [C], and feed [D] it into the TF Graph to get the prediction (y) as well as the cost.

Read the full article, click here.

@kdnuggets: “The Gentlest Introduction to #Tensorflow Part 2 #DeepLearning #MachineLearning @reculture_us”

In the previous article, we used Tensorflow (TF) to build and learn a linear regression model with a single feature so that given a feature value (house size/sqm), we can predict the outcome (house price/$).

The Gentlest Introduction to Tensorflow – Part 2