artificial intelligence Learns
Artificial Intelligence Learns :- In today’s world, technology plays a very important role. With every passing day technology just becomes bigger and better.
The technology of artificial intelligence Learns gradually taking control of most of our daily activities. Artificial Intelligence or Machine Intelligence is the intelligence which is displayed by a machine in contrast with the natural intelligence displayed by humans and other animals.
Artificial intelligence was founded in 1956 as an academic discipline. At the beginning it had to face many disappointments followed by loss of funding.
Later in the twenty-first century, with the advance in the power of computer and with large amounts of data and theoretical understanding, artificial intelligence Learns experienced resurgence and has become an essential part of the technology industry, helping to solve many challenging problems in computer science.
Recently an AI has been made which can learn the sense of fashion in a person and can invent the next outfit for that person. It can easily replace your personal stylist in the future and take his/her place.
In a research paper which has been published on the ArXiv, researchers from the University of California, San Diego, and Adobe has speculated that they can make an artificial intelligence Learns that can not only learn about a person’s sense of style but can also create computer generated images of the items to match the style.
This advanced artificial intelligence Learns system can predict broader fashion trends and can help retailers to create a personalized piece of clothing for them.
The research paper is based on two different algorithms. Firstly the researchers trained CNN (a convolutional neural network) the way to learn and classify the preference of a certain user.
To learn, the CNN used the purchase data which was scraped from Amazon in six categories: shoes, tops and pants for both men and women.
This type of model is common in the online retail world as this is used to pick other preferences which are being shown in the ‘Other items you might like’ section at the bottom of a page.
The second algorithm is based on the information to train GAN (a generative adversarial network). GAN is a type of artificial intelligence Learns that is very much proficient when it comes to the topic of generating realistic images.
GAN has two neural networks that learn directly from looking at the raw data. One of the networks generates a fake image based on the data set. The other network is programmed to use the same data to determine if the image is real or not.
GANs that were created by Ian Goodfellow could create fake faces of Hollywood stars. Though the faces were not perfect, some had blurred areas while some had no eyebrows.
But in case of fashion, the images used to train the networks were all shot from the same angle placed on white backgrounds making the images more convincing and easier.
Experts say that this project is basic and it is at its preliminary stage. This means that if a shopper likes black shirts, GAN would create more black shirts only.
However, the images produced by GAN are two-dimensional in nature. Researchers are working to change these two-dimensional images into 3D renderings that can make actual pieces of clothing.
Though there are certain limitations, it would not take much time for artificial intelligence to enter the world of fashion permanently.
Amazon is already working with some AI systems which would provide a greater advantage while spotting fashion trends. Amazon has also done some works with GANs.
Alibaba has launched a technology, named Fashion artificial intelligence Learns , which can recommend items to the shoppers on the basis of what they had brought into the dressing room.
The chief scientist of Vue.ai which is a fashion AI startup, Costa Colbert, recently revealed a method by which GANs can be used to make fake fashion models.
Costa Colbert says that UCSD and Adobe research papers can be very promising, but as it requires so much data it would be helpful only for the biggest names in online retail.
In the world of online fashion, GANs will continue to create waves. However, Colbert has pointed out that some companies already let their shoppers send their personal measurements to get customized pieces.
GANs can be a very cheap and fast way to show different options which are available to the users and can of course sell more items.