A new algorithm created by researchers at the Massachusetts Institute of Technology (MIT) has the capability to make a photograph more captivating and memorable at accuracy very much similar to that of humans.

As per the team, the algorithm can very well tell which faces, scenes and objects in photographs are more likely remembered by humans.

Lead author of the study Aditya Khosla said in a statement that understanding memorability can help them to make systems to capture the most important information or to store the information that most likely will be remembered by humans.

“It’s like having an instant focus group that tells you how likely it is that someone will remember a visual message”, he said.

Explaining the working of the algorithm, the researchers said when a photo is uploaded the algorithm called ‘MemNet’, it creates a heat map which indicates which parts of image are most memorable.

The team has induced the deep-learning (DL) technique into it. As per researchers DL is a branch of machine learning that can teach computers how to shift through bulks of data and find patterns by their own.

Study co-author Aude Oliva from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) said, although DL has led to progress in object recognition and scene understanding, still predicting human memory has been considered as a higher-level cognitive process that computer scientists will never be able cope with.

The findings of the researchers also shed light on the nature of human’s memory and how their memory can be improved if they view more memorable images.