HOME |
RSS | 
Obviously,
there's a lot of money to be made from hit pop songs. But can you predict
or even make which songs will make it ot the top of the charts?
Bring in the scientists! Artificial Intelligence researcher Tijl De Bie and colleagues analyzed 50 years' worth of hit songs on Britain's top 40 charts and came up with a formula.
From an interview over at The Los Angeles Times:
You used artificial intelligence to devise an equation that could predict which songs made it to the top of the charts. How does it work?
To predict the hit potential of a given song, we used a computer to quantify how similar it is to previous "hits" and "flops." Time frame is important: If you're scoring a song from today, then we will consider the songs in 2011 more important than the songs in the '60s.
We represent each song using a set of 23 different features that characterize the audio. Some are very simple features — such as how fast it is, how long the song is — and some are more complex features, such as how energetic the song is, how loud it is, how danceable and how stable the beat is throughout the song. We also took into account the highest rank that songs ever achieved on the chart.
The computer can combine a song's features in an equation that can be used to score any given song.
We can then evaluate how accurately the computer scored it by seeing how well the song actually did.
Every single week now we're updating our equation based on how recent releases have done on the chart. So the equation will continue to evolve, because music tastes will evolve as well.
Any good examples of the computer guessing correctly?
Wiley's "Wearing My Rolex" did well, strongly based on loudness. So that was an expected hit. It went to No. 2 in 2008.
Gnarls Barkley's "Crazy," which went to No. 1 in 2006, scored well thanks to its danceability, among other things.
Elvis Presley's "Suspicious Minds," which went to No. 2 in 1970, had a fairly simple harmonic movement, which at that time was a good thing if you wanted to score a hit.
Previously on Neatorama: Is There a Scientific Explanation for Justin Bieber?
If you thought the morning zoo crew on your local radio station were about as entertaining as robots, there may be more truth in that then you thought. One station in San Antonio has “hired” an artificially intelligent DJ named “Denise” to talk to listeners. Is this the end of the traditional radio DJ?
Meet Denise. She is not a real person, but instead, a personal assistant conjured up by Guile 3D Studio. She used to be a AI secretary, starting Aug 24th, she’ll be promoted to AI DJ at KROV in San Antonio. Denise cost a meager $200 when she was “hired” as a personal assistant to answer phone calls, Google things for people, check emails and make appointments. You know, the same kind of things you have your intern do after you’ve bought him for $200. It was radio personality Dominique Garcia‘s idea to promote Denise to DJ.
A robot that can learn, think and act for itself might make some people lose sleep over the possibility of a Terminator-esque robotic revolution, but scientists in Japan feel that this advancement in the field of robotics is a good thing, and may revolutionize how our mechanized workforces handle the tasks they’re designed to perform . Watch as this robot figures out how to do something it was never taught to do-pour a glass of ice water. Utterly fascinating to watch? Perhaps not, but this leap forward in artificial intelligence means science fiction is rapidly becoming science fact. Link -via Wired
Comments Off
If you were hoping that, after the Robopocalypse, you could earn your soylent green by flipping pancakes for our robot overlords, you’re out of luck. Human researchers at the Italian Institute of Technology have taught a robot how to do it. No, they didn’t refine it’s programming; the robot learned how to complete the task:
The video shows a Barrett WAM 7 DOFs manipulator learning to flip pancakes by reinforcement learning. The motion is encoded in a mixture of basis force fields through an extension of Dynamic Movement Primitives (DMP) that represents the synergies across the different variables through stiffness matrices. An Inverse Dynamics controller with variable stiffness is used for reproduction.
The skill is first demonstrated via kinesthetic teaching, and then refined by Policy learning by Weighting Exploration with the Returns (PoWER) algorithm. Compared to policy-gradient approaches, the reward is treated as a pseudo-probability, which allows Reinforcement Learning to use probabilistic estimation methods such as Expectation-Maximization (EM).
After fifty attempts, the robot became a competent pancake-flipper.
via Popular Science | Previously: Rapid Pancake Sorting Robot
Speech recognition technology reached 80% accuracy in 2001, then leveled off. The human ear has about 98% accuracy. Why haven’t computers improved in this area? Robert Fortner looks at several reasons.
Many spoken words sound the same. Saying “recognize speech” makes a sound that can be indistinguishable from “wreck a nice beach.” Other laughers include “wreck an eyes peach” and “recondite speech.” But with a little knowledge of word meaning and grammar, it seems like a computer ought to be able to puzzle it out. Ironically, however, much of the progress in speech recognition came from a conscious rejection of the deeper dimensions of language. As an IBM researcher famously put it: “Every time I fire a linguist my system improves.” But pink-slipping all the linguistics PhDs only gets you 80% accuracy, at best.
We can take comfort in knowing that the human brain is still way ahead of machines. Link -via Metafilter
(image source: Creative Coffins)
Sure, you could talk to actual human beings, but who would want to? Cleverbot, an artificial intelligence, is willing to have a conversation with you. Just start typing in the blank space. The program was developed by computer scientist Rollo Carpenter and his firm, Icogno Ltd.
Link via Geekologie | Screenshot: Geekologie | Video from Popular Science about the project
Stanford University’s robotics lab has built autonomous cars for several years. Recently, it established a land speed record for a robot car — 140 mph in an Audi TT-S nicknamed “Shelly”. But their next goal is even more ambitious: to have Shelly race the twisted dirt road that leads up to Pike’s Peak. Chris Dannen writes in Fast Company about the changes that allow the car to safely navigate sharper turns at higher speeds:
The new autonomous TT-S is markedly different from Junior, however. Junior was environmentally-aware; it had cameras that could see objects and road features, and it paired that data with GPS data. All that processing required two on-board Linux computers running quad-core Pentium chips and programmed in C and C++.
The new TT-S, unofficially dubbed “Shelly,” uses a different system. It has no cameras, only GPS, and a smaller, less powerful computing box running Sun’s Java Real Time System running on Solaris. Why? Despite Junior’s speedy processors, it still takes the car between 20-50 milliseconds to react to inputs from its sensory equipment. Because the TT-S “Shelly” is traveling at much higher speeds–the team has pushed it over 140 mph–even 20 milliseconds is too much of a delay.
You can view more videos of the project at the link.
Another step in the quest to create life has been made, as scientists successfully transformed one bacteria into another by replacing it’s DNA with a related species’. Now, scientists are setting their sights on creating entirely new microbes with unique genome sequences, from scratch.
Dr Venter likened it to “changing a Macintosh computer into a PC by inserting a new piece of software” and stressed it would be more difficult in other kinds of cells, which have enzymes to snip the DNA of invaders.
But he said to achieve the feat, without adding anything more than naked DNA, “is a huge enabling step.”
“It’s a necessary step toward creating artificial life,” added microbiologist Fred Blattner of the University of Wisconsin, Madison.
Dr Venter said that, in the light of this success, the culmination of a decade’s work, he will be attempting the first transplant of a lab-made genome to create the first artificial life “within months.”
From the Upcoming 
ueue, submitted by coconutnut.
