How Facebook Benefited From Machine Learning and Artificial Intelligence
First thing we have to know about what is Machine Learning?
Machine learning(ML) means to train the machine to work or think like a human mind using the historical data. Any technique used to create human-style reasoning in machines, Machine learning is a computer science term, is “a subset of AI describing techniques that allow a computer to improve on tasks with experience — using data to train itself, recognize patterns, and make predictions”. Machine learning is basically refers to Artificial Intelligence because using ML we can create AI.
Machine learning is a buzzword in the technology world right now, and for good reason.
A Machine learning algorithm is given a “teaching set” of data, then asked to use that data to answer a question. For example, you might provide a computer a teaching set of photographs, some of which say, “this is a cat” and some of which say, “this is not a cat.” Then you could show the computer a series of new photos and it would begin to identify which photos were of cats.
Machine learning then continues to add to its teaching set. Every photo that it identifies — correctly or incorrectly — gets added to the teaching set, and the program effectively gets “smarter” and better at completing its task over time.
Let’s See How Facebook Use Artificial Intelligence
We all have seen Facebook grow. It seems like yesterday that many of us were introduced to this new social network with a naïve impression of sharing pictures with friends and family. Today, the platform is considerably more robust and continually unfolds new features over basic networking with old friends. Facebook is building a business with long-term prospects where the role of Facebook Artificial Intelligence is unfathomable. Better yet, it is crucial.
Facebook has evolved as a platform enabling conversation and communication between people as a highly valuable source of knowing their lifestyle, interests, behavior patterns and taste inside and out. What do individual users like? What don’t they like? This data — voluntarily provide but messily structured — can be utilized for profit at an exorbitant value.
That’s where AI comes in. AI enables machines to learn to clarify data, all by themselves. The simplest example of this would be AI image analysis identifying a dog, without telling that machine what a dog looks like. This begins to give structure to unstructured data. It quantifies it and reprints it in the form from which understandable insights can then be generated.
Analyzing Text
A brilliant tool used by Facebook is called DeepText, which deciphers the meaning of the content posted to find the relative meaning. Facebook then generates leads with this tool by directing people to advertisers based on the conversations they are having. It offers the user related shopping links to connect chats and posts to potential interests.
Chatbots
From automated subscription content like weather and traffic to customized communication like receipts, shipping notifications and live automated messages, using the site has become easier and more efficient with chatbots at our service. Facebook has a powerful and highly functional bot API for the Messenger platform that does three functions smoothly.
🔆 Send/receive API- This API is all about sending and receiving text, images and rich bubbles comprised of multiple calls-to-action. A welcome screen for threads can also be created.
🔆 Message template- Facebook offers developers pre-made message template which allow customers to tap buttons and see beautiful, template images. This is much easier than having to code a new programming language for bot interaction. Structured messages with call-to-actions are amazingly user-friendly.
🔆 Welcome screen- Offering a tool to customize your experience, the Messenger app is all about better communication and retrieving the result as needed. And the welcome screen initiates this journey. Here people discover chatbots features and initiate the conversation.
Detecting Bad Content
The thorniest social media issues are always related to security and privacy. In addition to the already discussed, Facebook is using AI to detect content falling into seven main categories: nudity, graphic violence, terrorism, hate speech, spam, fake account and suicide prevention. AI helps identify fake accounts created for malicious purposes and shuts them down instantly.
Requiring the combined efforts of AI and the company’s community standards team, it is a tough nut to crack. It’s always difficult to track whether hate speech is actually there or if there is a nuance to be considered. That’s why the current scenario involves both AI automatically flagging potential hate speech along with follow-up manual review. In other areas, Facebook’s AI system relies on computer vision and raises a degree of confidence in order to determine whether or not to remove the content.
Facebook’s Leveraging of Machine Learning
Facebook was nice enough to show us the inner workings of how they build and scale ML infrastructure to support over 2 billion users. If you follow Facebook (in real life, not on their social media platforms) you’ll know their openness and willingness to share internal technical details is nothing new as they have a history of sharing innovations and their data center designs with the public through opencompute.org. Their AI platform can be categorized with these primary pillars:
Use Cases, Model Selection & Training
Facebook uses machine learning for classification, ranking and content understanding services. These include, but are not limited to, things like your news feed, serving ads, search, classifying objects, identifying people’s faces in posts and language translation from one country’s language to another’s. To build a platform like Facebook’s you will need to work across internal business units to take their use case and have your AI/ML leads select ML algorithms that are “best” for that particular use case. The “best” model being defined by attributes like how interpretable, simple, accurate, fast and scalable the model is. When training these models to achieve the desired accuracy, Facebook asks and answers these questions:
Computer vision models can take hours or days to complete depending on the size of the data sets. For models like news feeds they can train in a sub-hour fashion and update the online models in minutes.
FB Learner
We need an orchestration engine to assist with the entire ML workflow. To manage the ML workflow Facebook created FB Leaner.
FB Leaner has three primary components for processing Facebook’s Machine Learning Workflow
🔆 Feature Store- Helpful for data manipulation and feature extraction. Has an API for developers to use to interact with the feature store. Reduces development time as common features and model attributes can be stored here with associated metadata.
🔆 FB Learner Flow- Manages workflow processes required during training. Takes care of requesting required hardware, setting machines up in a cluster for training and packaging the models. Capable of easily reusing algorithms in different products and scaling to run thousands of simultaneous custom experiments.
🔆 FB Learner Predictor- Used for serving the models that other applications use to make inferences against. Provides an API to make inferences against the models easier.
