Deep-learning software attempts to mimic the activity in
layers of neurons in the neocortex, the wrinkly 80 percent
of the brain where thinking occurs. The software learns,
in a very real sense, to recognize patterns in digital
representations of sounds, images, and other data.
Google has been working on ways to use machine
learning and deep neural networks to solve some
of the toughest problems Google has, such as:
1.Natural language processing,
A program maps out a set of virtual neurons and then assigns random
numerical values, or “weights,” to connections between them. These
weights determine how each simulated neuron responds—with a
mathematical output between 0 and 1—to a digitized feature such as
an edge or a shade of blue in an image, or a particular energy level at
one frequency in a phoneme, the individual unit of sound in spoken
Programmers would train a neural network to detect an
object or phoneme by blitzing the network with digitized
versions of images containing those objects or sound
waves containing those phonemes.
If the network didn’t accurately recognize a particular
pattern, an algorithm would adjust the weights. The
eventual goal of this training was to get the network to
consistently recognize the patterns in speech or sets of
images that we humans know as, say, the phoneme “d” or
the image of a dog.
This is much the same way a child learns what a dog is by
noticing the details of head shape, behavior, and the like
in furry, barking animals that other people call dogs.
Neural nets (networks of functions that behave like neurons in the
human brain) have been around for a long time, since the late '60s,
but they're coming back into vogue for several reasons.
1.Neural nets, especially deep ones, is that they build features that describe
the data well automatically, without humans having to get involved .
2.There's a lot more computational power available,
3.A lot more labeled data,
4.People have figured out how to train very deep networks. Until four or five
years ago, it was impossible to get more than like a three-layer network to
train well because, since each computer neuron is a non-linear function, as
you get deeper and deeper its output gets more and more irregular. It's a
very difficult optimization process the deeper the network is. But people
have now figured out ways around that. You can pre-train on the first layer,
do your optimization there, get it into a good state, and then add a layer. You
can kind of do it layer by layer now.
1.Low power consumption (human brains use
about 20 watts, whereas the supercomputers
currently used to try to simulate them need
2.Fault tolerance (losing just one transistor can
wreck a microprocessor, but brains lose neurons
all the time);
3.A lack of need to be programmed (brains learn
and change spontaneously as they interact with
the world, instead of following the fixed paths and
branches of a predetermined algorithm).
Money is starting to be thrown at the question.
1.The European Human Brain Project has a €1
billion ($1.3 billion) budget over a decade.
1.The American BRAIN initiative’s first-year
budget is $100m,
Two of the most advanced neuromorphic programmes are being
conducted under the auspices of the Human Brain Project (HBP):
1.One, called SpiNNaker. It is a digital computer—ie, the sort familiar
in the everyday world, which process information as a series of ones
and zeros represented by the presence or absence of a voltage. It
thus has at its core a network of bespoke microprocessors. . To test
the idea they built, two years ago, a version that had a mere 18
processors. They are now working on a bigger one. Much bigger. Their
1m-processor machine is due for completion in 2014. With that
number of chips, Dr Furber reckons, he will be able to model about
1% of the human brain.
2.The other machine, Spikey, harks back to an earlier age of
computing. Several of the first computers were analogue machines.
These represent numbers as points on a continuously varying voltage
range—so 0.5 volts would have a different meaning to 1 volt and 1.5
volts would have a different meaning again. In part, Spikey works like
that. Analogue computers lost out to digital ones because the lack of
ambiguity a digital system brings makes errors less likely. But Dr
Meier thinks that because they operate in a way closer to some
Boeing and General Motors
Narayan Srinivasa, the project’s leader, says his
neuromorphic chip requires not a single line of
programming code to function. Instead, it learns by
doing, in the way that real brains do.
An important property of a real brain is that it is what is
referred to as a small-world network. Each neuron within
it has tens of thousands of synaptic connections with
other neurons. This means that, even though a human
brain contains about 86 billion neurons, each is within
two or three connections of all the others via myriad
The other SyNAPSE project is run by Dharmendra Modha at
IBM’s Almaden laboratory in San Jose. In collaboration with four
American universities (Columbia, Cornell, the University of
California, Merced and the University of Wisconsin-Madison),
he and his team have built a prototype neuromorphic computer
that has 256 “integrate-and-fire” neurons—so called because
they add up (ie, integrate) their inputs until they reach a
threshold, then spit out a signal and reset themselves.
In this they are like the neurons in Spikey, though the
electronic details are different because a digital memory is
used instead of capacitors to record the incoming signals.
From Web 2.0 to Webs 3.0 and 4.0: Swarms of
Nanotech 2: From PC to PM (Personal Manufactoring) , Baby Video,
Neurotech: Cyberkinetics' BrainGate brain-computer interface consists of a
computer chip that is a 2-mm-by-2-mm, 100-electrode array. Surgeons attach
the array like Velcro to neurons into the motor cortex. The electrodes send
information from 50 to 150 neurons at once, traveling through a fiber-optic
cable to a device about the size of a VHS tape (seen on back of wheelchair)
that digitizes the neuronal signals. Another cable from the digitizer runs to a
computer that translates the signal.
Microtubules are protein
structures found within cells.
They have diameter of ~ 24
nm and varying length from
several micrometers to
possible millimeters in axons
of nerve cells.
Roger Penrose has proposed
a theory of the quantum mind
in which the hollow cores of
microtubules inside neurons
form an environment capable
of supporting quantum-scale
information processing and
From Disk on Key to Hospital on Key
An Integrated Digital Microfluidic Lab-On-A-Chip for Clinical Diagnostics on Human Physiological