Skip to main content

🎓 Fundamental ML Concepts

  1. ML Model (Machine Learning Model):

    • A machine learning model is a mathematical representation or algorithm that learns patterns and relationships from data to make predictions or decisions without being explicitly programmed. It's the core component of machine learning systems.
    • Example: Suppose you want to build a model that predicts housing prices based on features like square footage, number of bedrooms, location, etc. The machine learning model in this case could be a regression model (e.g., linear regression) trained on historical housing data to predict prices for new properties.

  2. Fitting or Training the Model:

    • Fitting or training the model refers to the process of teaching the machine learning algorithm to learn patterns and relationships from the training data.
    • Example: In the housing price prediction example, fitting the model involves feeding the algorithm with a dataset of past housing prices along with corresponding features (e.g., square footage, number of bedrooms). The algorithm adjusts its internal parameters during training to minimize the difference between predicted prices and actual prices in the training data.

  3. Training Data:

    • Training data is the portion of data used to train or fit the machine learning model. It consists of input features (independent variables) and corresponding target labels or outcomes (dependent variables).
    • Example: Continuing with the housing price prediction, the training data includes historical housing data with features like square footage, number of bedrooms, location, etc., and the actual sale prices as the target labels. This data is used to train the machine learning model to predict housing prices accurately.

  4. Prediction:

    • Prediction refers to using a trained machine learning model to make forecasts or estimate outcomes for new, unseen data based on learned patterns from the training data.
    • Example: Once the housing price prediction model is trained, you can use it to predict the price of a new property that was not part of the training data. You input the new property's features (e.g., square footage, number of bedrooms) into the trained model, and it outputs a predicted price based on the patterns it learned during training.

In summary, a machine learning model is trained or fitted using training data to learn patterns and relationships, which allows it to make predictions or decisions (predictions) for new data based on the learned patterns.