Summary  
This chapter explains the trade-offs between traditional machine learning models and neural networks by comparing their complexity, data requirements, interpretability, training time, and computational needs, and offers guidelines for selecting the appropriate model type.

General domain of usage  
Predictive modeling

In machine learning, there are many model types. Two major groups are **traditional models** (linear regression, decision trees, SVMs) and **neural networks** (deep learning). They differ in complexity, data needs, and interpretability.

## How to Choose Between Them

1. **Dataset size:** small datasets → traditional models; large datasets → neural networks.
2. **Problem complexity:** simple patterns → traditional; complex tasks (e.g., images) → neural networks.
3. **Interpretability:** traditional models are easier to explain.
4. **Resources:** traditional models require less computation and train faster.

## Conclusion

There is no universal best choice. Understanding each model type’s **strengths** and **limits** helps you select what fits your **problem**, **data**, and **resources**. Experimentation remains the most reliable way to find the right approach.


Which model type is more interpretable by design?

For a large dataset with complex, non-linear patterns, which model type might be more suitable?

In which scenario might you prioritize using a traditional model over a neural network?

Neural networks are powerful algorithms inspired by the structure of the human brain that are used to solve complex machine learning problems. You will build your own Neural Network from scratch to understand how it works. After this course, you will be able to create neural networks for solving classification and regression problems using the scikit-learn library.

First, we will discuss what a neural network is and how it works. And also consider the scope of its application.

Next, we will try to build our own neural network and see how efficiently it copes with learning. We will also consider a ready-made solution from the scikit-learn library.

Finally, we will give you some additional useful information on how to understand which model to use and what types of neural networks there are. To complete the course, you will be tested on your acquired knowledge.

Neural Networks or Traditional Models

Differences

Limitations

How to Choose Between Them

Conclusion

1. Which model type is more interpretable by design?

2. For a large dataset with complex, non-linear patterns, which model type might be more suitable?

3. In which scenario might you prioritize using a traditional model over a neural network?