Why is there a difference between a maths predictor and a pattern predictor?

Question

While going through the neural network lessons, I found out that "learning math" and "learning patterns" are very different. Why? Surely a neural network is a neural network? Only thing that changes is the activation function and the input/output right? Why should code be so different? On brain.js, I made a pattern and maths predictor using brain.NeuralNetwork(), the same method. Why is it different in Python?

Answer 1

Predictive models
Predictive model uses predictive models to analyze the relationship between the specific performance of a unit in a sample and one or more known attributes or features of the unit. See Clueless Coder it basically do the objective of the model is to assess the likelihood that a similar unit in a different sample will exhibit the specific performance. This category encompasses models in many areas, such as marketing, where they seek out subtle data patterns to answer questions about customer performance, or fraud detection models. Predictive models often perform calculations during live transactions, for example, to evaluate the risk or opportunity of a given customer or transaction, in order to guide a decision. With advancements in computing speed, individual agent modeling systems have become capable of simulating human behaviour or reactions to given stimuli or scenarios.

The available sample units with known attributes and known performances is referred to as the "training sample".

Answer 2

I think now it should be clear if yet it's hard to understand let me know
Happy learning 👍