IBM has trained an AI to help humans develop new fragrances for perfumes and other products. The system is called Philyra, and it involves machine learning algorithms that find new combinations of scents to produce novel fragrances. According to IBM, its AI can comb through existing combinations to spot “whitespaces” in which entirely new formulas can be formed.
IBM named its AI after the Greek goddess of fragrance and created it to augment the work of human experts. The system is able to sift through hundreds of thousands of formulas, as well as thousands of raw fragrance materials, according to the company. Using these, the technology figures out new combinations for all-new fragrances.
IBM teamed with Symrise to create the system, which is able to determine which raw materials complement others, which can be substituted, the right doses for these compounds, and how humans are likely to react to the scent. This includes determining whether the fragrance is masculine or feminine and the novelty of it in comparison to fragrances already on the market.
According to the company, Symrise used the AI to design two new perfume products, both of which will be released next summer. Humans were involved in this process, tweaking the formula developed by the machine. IBM explains that the technology helps reduce the time consuming initial steps, enabling human experts to focus on refining a formula instead of trying to create new fragrance combos.
This same machine learning technology could be put to work creating other new products, such as new flavors and shampoos, according to IBM. It’s possible that an AI like Philyra may one day be put to use by companies around the globe to design new products, expediting the creation process.