Share this post:
While IBM Watson is an expert at tackling business and societal challenges like water shortages in California, cognitive systems can also be creative – from testing ingredient combinations and creating unusual recipes to helping designers consider unique combinations of colors and fabrics for a new cognitive dress.
Developer teams are working constantly and creatively, using platforms like IBM cloud to collaborate and tinker with new solutions that will make Watson smarter. Thinking outside of the box is key – inspiration can strike at any time and can even emerge from fantasy novels.
As any Potterhead can tell you, the house that the Sorting Hat chooses for each of the students determines their entire experience at Hogwarts – J.K. Rowling’s legendary School of Witchcraft and Wizardry.
For those not familiar with Harry Potter, the students are each placed into one of the school’s four houses – Gryffindor, Ravenclaw, Hufflepuff, and Slytherin – which is a decision determined by the Sorting Hat.
Depending on their character traits – such as bold and brave for Gryffindor – the hat places the wizard or witch into whichever house it thinks he or she belongs to.
Even for Harry Potter, the Sorting Hat had to contemplate about which house he belonged to. Harry had “plenty of courage,” “not a bad mind,” and “a thirst to prove [him]self,” all characteristics of Gryffindor and Slytherin, and so the Sorting Hat had a difficult choice to make – the hat ultimately decided on the most confident option.
As a Solutions Architect for the IBM ecosystem, I decided to bring fantasy to reality by creating a real-life Sorting Hat with the help of my seven-year-old daughter, Watson, and BlueMix, IBM’s cloud platform.
A blend of innovation and craftiness led to the creation of the real-life sorting hat. The exterior is simple – a bike helmet and metal wiring to create the frame and a cotton black t-shirt for the cloth.
But the real magic is in one of the dozens of Watson APIs available on BlueMix known as the Natural Language Classifier (NLC) API. NLC interprets and understands the meaning behind text, categorizes this meaning, and prompts specific actions such as providing a corresponding answer to a question with confidence.
The NLC needed to be trained, which is when I turned to my daughter, Lucy, for help. A domain expert in Harry Potter, Lucy and I built a Ground Truth, a data set that teaches the NLC on how to behave.
By identifying characteristics that make up each house – Gryffindor: bold and daring, Ravenclaw: clever and brainy, Hufflepuff: just and loyal, and Slytherin: ambitious and cunning – we created a Ground Truth for the Sorting Hat.
To test its accuracy, I described the characteristics of certain prominent public figures to the hat. The results were encouraging: Vice President Joe Biden – Gryffindor (69%), the 39th President of the United States Jimmy Carter – Hufflepuff (54%), theoretical physicist Stephen Hawking – Ravenclaw (97%), and legendary folk singer Pete Seeger – Gryffindor (77%). The higher the percentage, the more likely that person reflects the characteristics of the corresponding house.
I’m among the more than 80,000 developers building cognitive solutions on the Watson Developer Cloud, a cognitive development environment fueled by IBM Cloud.
I consider myself a real tinkerer, having several side projects. In addition to the hat, I’ve created a wine and food pairing solution and have also created multiple voice-command toys, including a responsive Mr. Potato Head.
These projects are examples of how easily developers can use IBM Cloud to play with and apply Watson solutions to everyday business challenges – whether it’s interpreting a customer’s intent through analyzing their spoken word or classifying the vast world of unstructured data.