Google using machine learning
NEW DELHI: Tech giant Google is doing everything possible to get rid of spam mail. The company has now taken the help of the in-house machine learning system. Called TensorFlow, this tool will help filter additional spam for Gmail users. The company started using new filters last month and claimed that it has been able to block an additional 100 million spam messages every day with its help.
TensorFlow was originally developed for Google’s internal use. The company had released Machine Learning Framework three years ago under the Apache 2.0 license. The company claims that since then, developers from around the world have produced 71,000 forks of public code and other open source contributions.
As The Verge has stated, the company says that adding TensorFlow to Gmail will enable it to better personalize spam filters. This whole process is going on for years, where Gmail searches for certain signals from users, on the basis of which it verifies spam. However, with TensorFlow, the company is now able to convert these signals into better results.
The report says, “TensorFlow makes it easy to manage this data on a large scale, whereas the open-source nature of the framework means that new research of the community can be quickly integrated.”
In addition, GI is also using AI with rule-based filters. Rule-based filters are able to block obvious spam, while machine learning looks for new patterns that explain whether an email relies on spam.
Recently, it was reported that Google is planning to introduce three new features in Gmail. These three features have been borrowed from Inbox by Gmail. As told by XDA developers, these new features will be available first on Android. There are three feature bundles coming soon in Gmail which will keep all the newspapers in a single place from the published publication. Another feature in the pin, which allows users to pin all emails from the sender for easy communication and the third feature is a reminder.