Google Launches AI-Powered Game Called Emoji Scavenger Hunt

Emoji Scavenger Hunt

Google has created a new Artificial Intelligence (AI) experiment new game called “Emoji Scavenger Hunt”  that uses the company’s advanced machine learning tools.The game experiment asks the user to use a smartphone's camera to find objects that match an emoji within a time limit.With each find, the time limit increases, The Verge reported on Saturday.This comes a few days ahead of Google's I/O developer conference slated to be held from May 8 in California.

“Locate the emoji we show you in the real world with your phone’s camera. A neural network will try to guess what it’s seeing. Make sure your sound is on,” says Google on its website. Google makes it clear that it does not store any images on its servers. “All the interactions are happening locally on your device,” added Google.

To play the game, you need to visit this website - emojiscavengerhunt.withgoogle.com- on your Android or iPhone browser. Note that the game only works on mobile devices, not on the desktop. Give the website permission to access your camera. The first scavenger hunt is pretty easy, say it will ask you to find things that look like your plam, keyboard or mouse, which can be found in your vicinity easily. You can also share your scores on social networking platforms like Twitter and Facebook.

How to Play Game :

According to the report, the company could announce some AI news. Google reportedly might update its AI camera app, Google Lens and its specialised AI chips known as TPUs. Last month, Google gave users a (fun) glimpse of how far natural language processing -- that deals with machine reading comprehension -- in the technology has come. Google Research division of the search giant has rolled out Semantic Experiences, which are websites with interesting activities that demonstrate AIs' ability to understand how we speak.

Complex algorithm behind a simple AI game

The game is based on Tensorflow.js, a platform for browser based JavaScript library for training and deploying ML models. The platform allows developers to use highly advanced machine learning tools in web browsers. Developers can learn on how to make similar AI games or apps here. You can also check out Google’s other AI experiments here.

It has two experiences to enjoy and the third one is for developers to help them create their own experience. The first two experiences are called “Talk to Books” in which users can explore a new way to interact with books, and “Semantris” where people can play word association games powered by semantic search.

The company trained its AI by feeding it a “billion conversation-like pairs of sentences”, so it can learn to identify what a good response looks like.