AI Platform enables many parts of the machine learning workflow. This document provides an introductory description of the overall ML process and explains where each AI Platform service fits into the process.
Definition
Machine learning (ML) is a subfield of artificial intelligence (AI). The goal of ML is to make computers learn from the data that you give them. Instead of writing code that describes the action the computer should take, your code provides an algorithm that adapts based on examples of intended behavior. The resulting program, consisting of the algorithm and associated learned parameters, is called a trained model.
Stages
The entire learning process begins when we provide a machine learning model to adjust its internal parameters and also we can tweak these parameters so that the model can explain and analyze the data better. This entire process is normally known as a machine learning workflow. So, machine learning workflow can be described in many ways as per the process to train the data models. But still, the basic ML workflow will remain the same and it consists of the below stages.
- Source and prepare your data
- Develop our data model
- Train a Machine Learning Model on our data model and evaluate data accuracy
- Now, deploy your trained model
- Send the prediction request to your model
- Analyze the predictions on an ongoing process
Sources
You must have access to a large set of training data that includes the attribute (called a feature in ML). That you want to be able to infer (predict) based on the other features. For example, assume you want your model to predict the sale price of a house. Begin with a large set of data describing the characteristics of houses in a given area, including the sale price of each house. Having sourced your data, you must analyze and understand the data and prepare it to be the input to the training process.
Evaluation
AI Platform provides the services you need to train and evaluate your model in the cloud. In addition, AI Platform offers hyperparameter tuning functionality to optimize the training process. When training your model, you feed it data for which you already know the value for your target data attribute (feature). You run the model to predict those target values for your training data, so that the model can adjust its settings to better fit the data and thus to predict the target value more accurately. Similarly, when evaluating your trained model, you feed it data that includes the target values. You compare the results of your model’s predictions to the actual values for the evaluation data and use statistical techniques appropriate to your model to gauge its success.
Machine Learning Workflow is one of the popular techniques for any application developer. currently all the things in the company done by manually which will be replaced by the machine in the future with the help of machine learning. So, the revolution of the machine learnings will be staying with us for a long time.
