actually might be indicating that a
child is at risk,” Lindsey says. They
need to learn that at-risk youth may
express irritability rather than sad-
ness as a warning sign. Physical
symptoms could be important, too:
Lindsey’s research has shown that
depressed Black youth who live in
low-income housing sometimes
complain of physical pain. Interven-
tions that aim to reduce the stigma
associated with mental health
treatment in Black communities are
now becoming available. Lindsey and
his colleagues developed a program
called the Making Connections
Intervention to provide depressed
young people with mental health
care and reduce the stigma associat-
ed with receiving it.
Another goal of such interventions
should be to convey the message to
Black children and teenagers that
they are valued members of society.
Right now there is a “lack of compas-
sion and care for young Black lives,”
Goodwill says, which may be fueling
feelings of worthlessness. We must
counteract this pernicious message,
she says, so that young Black people
in America understand that “their lives
are full of meaning and purpose.”
—Melinda Wenner Moyer
The Brain Guesses
What Word
Comes Ne-
Like some AI systems, the organ
of thought appears to predict
what word follows another to coax
meaning from languageIn the midst of a conversation with
an acquaintance, your brain might
skip ahead, anticipating the words
that the other person will say.
Perhaps then you will blurt out
whatever comes to mind. Or maybe
you will nurse your guess quietly,
waiting to see if—out of all the
hundreds of thousands of possibili-
ties—your conversational partner will
arrive at the same word you have
been thinking of. Amazingly, your
companion will often do so.
How does the brain do this?
Figuring out how we process
language has long been a focus for
neuroscientists. Massachusetts Insti-
tute of Technology researchers
brought a new take to the question
using a technique called integrative
modeling. They compared dozens of
machine-learning algorithms calledneural networks with brain scans
and other data showing how neural
circuits function when a person
reads or listens to language. The
researchers had a two-part goal:
they wanted to figure out how the
brain processes language and in
doing so push the boundaries of
what machine-learning algorithms
can teach us about the brain.The modeling technique reveals
that a key role may be played by
next-word prediction, which is central
to algorithms such as those that
suggest words as you compose your
texts and e-mails. The researchers
discovered that models that excel at
next-word prediction are also best
at anticipating brain-activity patterns
and reading times. So it seems like Elen11/Getty ImagesNEWS