Télécharger la présentation

mlops course

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

Playing audio...

  1. Machine Learning Algorithms and Where they are Used? We will now learn how Machine Learning (ML) works in this Machine learning basics for beginners tutorial explained in mlops course: Machine learning is the brain in which all learning occurs. The machine learns in the same way that humans do. Experience teaches humans. The more we know, the better we can predict. By analogy, when we face an unknown situation, our chances of success are lower than when we face a known situation. Machines are trained in the same manner. The machine looks at an example to make an accurate prediction. When given a similar example, the machine can predict the outcome. However, the machine, like a human, has difficulty predicting if it is fed a previously unseen example. The primary goal of machine learning is to learn and infer. First and foremost, the machine learns by discovering patterns. This discovery was made possible by data. One critical role of the data scientist is to carefully select which data to provide to the machine. A feature vector is a list of attributes used to solve a problem. A feature vector can be thought of as a subset of data that is used to solve a problem. The machine employs sophisticated algorithms to simplify reality and convert this discovery into a model. As a result, the learning stage is used to describe and summarize the data into a model. When the model is finished, it can be tested on never-before-seen data to see how powerful it is. The new data is transformed into a features vector, which is then run through the model to provide a prediction. This is the most beautiful aspect of machine learning. There is no need to retrain the model or update the rules. You can use the previously trained model to infer new data. Assume you need to predict a customer's gender for a commercial. From your customer database, you will begin collecting information such as height, weight, job, salary, purchasing basket, and so on. You know the gender of each of your customers; it can only be male or female. The classifier's goal will be to assign a probability of being male or female (i.e., the label) based on the data (i.e., features you have collected). When the model has learned to recognise male and female faces, you can use new data to make a prediction. For example,

  2. suppose you recently received new information from an unknown customer and want to know whether he or she is male or female. If the classifier predicts male = 70%, it means that the algorithm is confident that this customer is 70% male and 30% female. The label can belong to two or more categories. The Machine Learning example above has only two classes, but if a classifier is required to predict an object, it has dozens of classes (e.g., glass, table, shoes, etc. each object represents a class)

More Related