色花堂app

鈥淭here鈥檚 this problem in the artificial intelligence field known as the long-range dependency problem,鈥� explains Dr. Paul Bodily, Assistant Professor of Computer Science at ISU. 鈥淏asically, it鈥檚 really hard for AI to generate sequences of elements鈥� like music or language鈥攚here what elements are chosen in one part of the sequence depend on what elements are chosen in a completely different part of the sequence. For example, musicians may want to have a chorus repeat in different places in a song or have lyrics at different positions rhyme. It is simple enough to copy and paste or separately generate interdependent sequences of notes. But typically, these approaches mean sacrificing the natural flow or coherency between the interdependent elements, and that鈥檚 where the challenge lies.鈥� 

 

Enter . Pop* - pronounced 鈥榩op star鈥� - is an AI system developed by Bodily. It is designed to operate without needing a human and, most importantly, solves the long-range dependency problem. 

 

鈥淧op* uses a special type of machine learning model that looks way ahead in the sequence at what will eventually be generated to adjust the probabilities of what it generates in the short run,鈥� Bodily said. 鈥淚n the end, the piece is coherent all the way through.鈥�

 

Bodily used well-known songs like 鈥淭winkle, Twinkle Little Star,鈥� and 鈥淪omewhere Over the Rainbow,鈥� as well as pop classics like 鈥淗ey Jude鈥� by The Beatles and John Lennon鈥檚 鈥淚magine鈥� to train Pop* on chords, pitches, rhythms, and lyrics. After this crash course training phase, the AI can now compose its own short pop songs. For lyrical inspiration, Pop* looks to Twitter for tweets on its favorite themes: being in love, feeling depressed, and new beginnings.

 

鈥淥ne of the first compositions Pop* generated was this really somber, pensive song with the lyrics that went, 鈥楢nd I think I am just a lie,鈥� Bodily explained. 鈥淚 was floored by how much it moved me. We humans all deal with feelings of inadequacy at times, but beyond that, here is an AI system that seems to be questioning its own validity and doing so in an artistic, creative way.鈥�

 

Recently, a paper by Bodily and co-researcher Dr. Dan Ventura, Professor of Computer Science at Brigham Young University, was published in the . The publication marks the culmination of years of work by Bodily, starting when he was working on his doctorate at BYU under the instruction of Ventura. 

 

鈥淲hen I started doing research in AI, I was already heavily involved in a completely different research direction, and it was a big leap of faith to switch,鈥� Bodily said. 鈥淭his publication represents the reward for taking that leap seven years ago.鈥�

 

In June, Pop* will be entering a battle of the bands of sorts, the , and will be competing using one of its earliest compositions, 鈥淎nd I Think I.鈥� Looking to the future, Bodily aims to research the use of systems like Pop* for therapeutic purposes. He鈥檒l be looking into how pairing people with an AI that knows how to compose music can help enhance their ability to be creative and process whatever challenges they may be going through.

 

鈥淢y vision is to integrate Pop* into a mobile app in which the user is prompted for thoughts or feelings, and then Pop* and the user work together to create a meaningful musical expression of or reaction to those ideas. The system could be designed to help the user share these creations or find other like-minded creators with whom they could connect. My hypothesis is that a tool like that could be quite powerful in helping people address various mental health challenges.鈥�

 

If you鈥檇 like to hear some of the songs composed by Pop*, visit the website for Bodily鈥檚&苍产蝉辫;.  

 

For more information on the 色花堂app Department of Computer Science, visit .