jueves, 10 de diciembre de 2015

A Learning Advance in Artificial Intelligence Rivals Human Abilities


Humans and machines were given an image of a novel character (represented atop each grid) and then asked to copy it. CreditBrenden Lake

Computer researchers
advances on Thursday
that surpassed human
 capabilities for a narrow
set of vision-related tasks.

The improvements are
noteworthy because
so-called machine-vision
systems are becoming
commonplace in many
aspects of life, including
car-safety systems that
detect pedestrians and
bicyclists, as well as in
video game controls,
Internet search and
factory robots.
Researchers at the Massachusetts Institute of Technology,
New York University
and the University of Toronto reported a new type of
“one shot”
machine learning on Thursday in the journal Science, in
which a computer
vision program outperformed a
group of humans in identifying handwritten characters based on a single example.
The program is capable of quickly learning the characters in a range of languages and generalizing from what it has learned. The
authors suggest this capability is similar to the way humans
learn and understand concepts.
The new approach, known as Bayesian Program
Learning, or B.P.L., is different from current machine learning technologies known as deep neural networks.
Neural networks can be trained to recognize human speech,
detect objects in images or identify kinds of behavior by being
exposed to large sets of examples.
Although such networks are modeled after the behavior of
biological neurons, they do not yet learn the way humans do —
acquiring new concepts quickly. By contrast, the new software program described in the Science article is able to learn to recognize
handwritten characters after “seeing” only a few or even a single
The researchers compared the capabilities of their
Bayesian approach and other programming models using five separate learning tasks that involved a set of characters from a research data set known as Omniglot, which includes 1,623 handwritten character
sets from 50 languages. Both images and pen strokes needed
to create characters were captured.
“With all the progress in machine learning, it’s amazing what
you can do with lots of data and faster computers,” said
Joshua B. Tenenbaum, a professor of cognitive science and
at M.I.T. and one of the authors of the Science paper. “But
when you look at children, it’s amazing what they can
learn from very little data. Some comes from prior knowledge
and some is built into our brain.”
Also on Thursday, organizers of an annual academic machine vision competition reported gains in lowering the error rate in
software for finding and classifying objects in digital images.


Three researchers who have created a computer model that captures humans’ unique ability to learn new concepts from a single example: from left, Ruslan Salakhutdinov, Brenden M. Lake and Joshua B. Tenenbaum. CreditAlain Decarie for The New York Times

“I’m constantly amazed by the rate of progress in the field,”
said Alexander Berg, an assistant professor of computer 
science at the University of North Carolina, Chapel Hill.
The competition, known as the Imagenet Large Scale
Visual Recognition Challenge, pits teams of researchers at
academic, government and corporate laboratories against one another to design programs to both classify and detect objects. It was
won this year by a group of researchers at the Microsoft Research laboratory in Beijing.
The Microsoft team was able to cut the number of errors in
half in a task that required their program to
classify objects from a set of 1,000 categories. The team also
won a second competition by accurately detecting all instances
of objects in 200 categories.
The contest requires the programs to examine a large number
of digital images, and either label or find objects in the images.
For example, they may need to distinguish between objects 
such as bicycles and cars, both of which might appear to have 
two wheels from a certain perspective.
In both the handwriting recognition task described in Science
and in the visual classification and detection competition,
researchers made efforts to compare their progress to human
In both cases, the software advances now appear to surpass
human abilities.
However, computer scientists cautioned against drawing
conclusions about “thinking” machines or making direct
comparisons to human intelligence.
“I would be very careful with terms like ‘superhuman
performance,’ ” said Oren Etzioni, chief executive of the Allen Institute for Artificial Intelligence in Seattle. “Of course the calculator
exhibits superhuman performance, with the possible exception of
Dustin Hoffman,” he added, in reference to the actor’s portrayal
of an autistic savant with extraordinary math skills in the
movie “Rain Man.”
The advances reflect the intensifying focus in Silicon Valley
and elsewhere on artificial intelligence.
Last month, the Toyota Motor Corporation announced a
five-year, billion-dollar investment to create a research center
 based next to Stanford University to focus on artificial
 intelligence and robotics.
Also, a formerly obscure academic conference, Neural
Information Processing Systems, underway this week in
Montreal, has doubled in size since the previous year and
has attracted a growing list of brand-name corporate sponsors,
including Apple for the first time.
“There is a sellers’ market right now — not enough talent to
fill the demand from companies who need them,” said
Terrence Sejnowski, the director of the
Computational Neurobiology Laboratory at the Salk Institute
for Biological Studies in San Diego. “Ph.D. students are
getting hired out of graduate schools for salaries that are
higher than faculty members who are teaching them.”