Microsoft_ML-For-Beginners

1.0: INTRODUCTION

On a high level, the craft of creating machine learning (ML) processes is comprised of a number of steps:

1. Decide on the question. Most ML processes start by asking a question that cannot be answered by a simple conditional program or rules-based engine. These questions often revolve around predictions based on a collection of data.
2. Collect and prepare data. To be able to answer your question, you need data. The quality and, sometimes, quantity of your data will determine how well you can answer your initial question. Visualizing data is an important aspect of this phase. This phase also includes splitting the data into a training and testing group to build a model.
3. Choose a training method. Depending on your question and the nature of your data, you need to choose how you want to train a model to best reflect your data and make accurate predictions against it. This is the part of your ML process that requires specific expertise and, often, a considerable amount of experimentation.
4. Train the model. Using your training data, you'll use various algorithms to train a model to recognize patterns in the data. The model might leverage internal weights that can be adjusted to privilege certain parts of the data over others to build a better model.
5. Evaluate the model. You use never before seen data (your testing data) from your collected set to see how the model is performing.
6. Parameter tuning. Based on the performance of your model, you can redo the process using different parameters, or variables, that control the behavior of the algorithms used to train the model.
7. Predict. Use new inputs to test the accuracy of your model.

2.0: REGRESSION

This topics covers the content of linear and logistics regression, and how to use them. Regression models can help determine the relationship between variables. This type of model can predict values such as length, temperature, or age, thus uncovering relationships between variables as it analyzes data points.

Lessons

1-Tools

2-Managing Data

3-Linear and polynomial regression

4-Logistic regression

3.0: WEB-APP

4.0: CLASSIFICATION

5.0: CLUSTERING

6.0: NLP

7.0: TIMESERIES

8.0: REINFORCEMENT

9.0: REAL-WORLD