Beware the quantum computers
Today’s encryption technology will be putty in the hands of those running the post-quantum world. How equipped ...
Researchers have developed a “DJ-like” algorithm that can create ultra-personal music playlists which adapt to listeners’ changing moods.
The algorithm called DJ-MC could outdo streaming music services by making playlists that change depending on each individual’s shifting emotion, according to the research published in the journal MIS Quarterly.
“Whether you’re getting into the car after a long day of meetings, or you’re getting out of bed on a weekend morning, it should tailor its recommendations to your changing moods,” said Maytal Saar-Tsechansky, a professor at the University of Texas at Austin in the US.
The programme runs a series of feedback loops. It tries out a song, the listener rates it, and the application heeds that rating in choosing the next song.
“Then you alter the model accordingly,” said Elad Liebman, a PhD student in computer science at UT Austin, who conceptualised the programme.
DJ-MC adapts to the listener’s mood, considering not only which songs they will enjoy, but also in what order, the researchers said.
Songs are organised intelligently, leading to an expressive,”DJ-like” sequence, instead of a random, arbitrary-sounding one, they said.
According to the researchers, DJ MC plans its moves ten songs ahead, like a chess player.
While one song is playing, the programme generates tens of thousands of possible sequences, and it predicts which one will please the listener the most, they said.
The programme serves up the next song on that playlist -- and while that song is playing, it creates and tests new sequences.
The researchers noted that in machine learning, the mechanism is known as a Monte Carlo search which inspired the name of the programme: DJ-MC.
The programme could be adapted to other kinds of media, from news stories to videos, they said.
“Learning algorithms don’t have a taste; they just have data. You can replace the dataset with anything, as long as people are consuming it similarly,” Liebman said.
Today’s encryption technology will be putty in the hands of those running the post-quantum world. How equipped ...
Rocketship’s Anand Rajaraman on getting pitches from places like Rameswaram and Patna
Bengaluru-based Archeron group plans to open five banks that are run entirely by AI and quantum technologies
Ably skippered by N Srinivasan, India Cements is upping its post-Covid-19 game by expanding capacity
Fiscal stimulus, friendly monetary policy and firm commodity prices point towards normalcy, says the MD and ...
Price correction is a good opportunity for long-term investors to take the plunge
Q4 earnings, along with progress in controlling Covid-19 spread, will be in focus
Do keep in mind that premium may go up in case one of the members has a pre-existing condition
In an age of falling female workforce participation, worsened by the Covid-19 pandemic, policy makers and ...
Of an injured baby goat, young men on motorcycles and political tensions
It’s the birthday of Muttiah Muralitharan — the man who took a staggering 800 test wickets. What better way to ...
An ode to writer and great-uncle Ved Mehta, and Ekarat, the friend who wrote and quit on his own terms
Marketers are padded up, sponsorship deals have been struck, and campaigns are rolling out. Now let the games ...
And what marketers can possibly do to bring it back in our lives
The agency has changed form over the years but its lustre has not dimmed
Media Factory has purchased the majority stake held by Sam and Lara Balsara of Madison World in Madison Media ...
Three years after its inception, compliance with GST procedures remains a headache for exporters, job workers ...
Corporate social responsibility (CSR) initiatives of companies are altering the prospects for wooden toys of ...
Aequs Aerospace to create space for large-scale manufacture of toys at Koppal
And it has every reason to smile. Covid-19 has triggered a consumer shift towards branded products as ...
Please Email the Editor