This repository shows my journey into study of deep learning and neural network (Machine Learning)
Blessing Nehohwa
A machine learning algorithm is like a black box that we feed input data and it delivers an output.
-
Data : Readily available historical data
-
Model : We need a model the simplest model we can train is a linear model stepping upon linear model.
Deep machine learning lets us create complicated non-linear models- these usally fit the data much better than a simple linear model
It all boilsi down to optimising this function.
If our model is measuring the prediction error of the model we would want to minimize this error, minimise the objective function -
Objective Function: Is the Measure used to evaluate how well the model's outputs match the desired correct values.