FUNDAMENTALS:-

Machine learning is a subset of AI (Artificial Intelligence)

• Definition:

  Machine Learning is the process of developing a model (or machine) and training it using large amounts of data.

• Learning Patterns:

  The model analyses the input data to identify and learn underlying patterns or relationships within it.

• Making Predictions:

  Once trained, the model can handle new, unseen data recognizing patterns, interpreting it, and generating results or answers with a certain level of accuracy.

• Accuracy Improvement:

  The more relevant data we provide during training, the better the model becomes at making accurate predictions.

USAGES:-

• Language Processing
• Self-Driving Cars
• Robots
• Games

ML PIPELINE:-

A machine learning project typically involves a number of steps.

1. Import the data : Data is often imported in the form of a CSV file.
2. Clean the data : Data cleaning can involve several tasks, such as:
   • Removing duplicates, as they can confuse the model.
   • Handling missing values to ensure complete data.
   • Identifying and removing extreme values that can distort the model's learning.
   • Making text data consistent (e.g., converting to lowercase, removing punctuation, eliminating extra spaces). How data is cleaned depends on the specific project and data type.
3. Split the data : The clean dataset needs to be split into two segments - one for training the model and one for testing it. For example, 80% could be used for training and the other 20% for testing. This splitting is typically done after importing and cleaning the data.
4. Create a model : This involves selecting an algorithm to analyse the data. There are many machine learning algorithms available, such as decision trees and neural networks. The choice of algorithm depends on the problem being solved and the input data. We don't have to program the algorithm , as there are many publicly available libraries on the internet.
5. Train the model : The model is trained by feeding it the training data. The model learns patterns in the data during this step.
6. Make predictions : Once trained , the model can be asked to make predictions. Predictions may not always be accurate, especially at the beginning.
7. Evaluate and improve : The final step is to evaluate the predictions and measure the accuracy of the model. If the accuracy scores are low, you might select a different algorithm or fine-tune the parameters of the existing model to optimise accuracy. Evaluating accuracy involves comparing the model's predictions on the test data with the actual values in the test set. The source notes that the more data used for training and the cleaner the data, the more accurate the model is likely to be.