| |
KF5JRV > TECH 19.07.16 12:40l 42 Lines 2585 Bytes #999 (0) @ WW
BID : 6290_KF5JRV
Read: GUEST
Subj: Artificial Neural Networks
Path: IZ3LSV<F1OYP<ON0AR<OZ5BBS<CX2SA<N0KFQ<KF5JRV
Sent: 160719/1130Z 6290@KF5JRV.#NWAR.AR.USA.NA BPQK1.4.65
The Inspiration for Artificial Neural Networks, Building Blocks of Deep
Learning 1959
In 1959 Harvard neurophysiologists David H. Hubel and Torsten Wiesel, inserted
a microelectrode into the primary visual cortex of an anesthetized cat. They
then projected patterns of light and dark on a screen in front of the cat, and
found that some neurons fired rapidly when presented with lines at one angle,
while others responded best to another angle. They called these neurons
"simple cells." Still other neurons, which they termed "complex cells,"
responded best to lines of a certain angle moving in one direction. These
studies showed how the visual system builds an image from simple stimuli into
more complex representations. Many artificial neural networks, fundamental
components of deep learning, may be viewed as cascading models of cell types
inspired by Hubel and Wiesel's observations.
For two later contributions Hubel and Wiesel shared the 1981 Nobel Prize in
Physiologist or Medicine with Roger W. Sperry.
". . . firstly, their work on development of the visual system, which involved
a description of ocular dominance columns in the 1960s and 1970s; and
secondly, their work establishing a foundation for visual neurophysiology,
describing how signals from the eye are processed by the brain to generate
edge detectors, motion detectors, stereoscopic depth detectors and color
detectors, building blocks of the visual scene. By depriving kittens from
using one eye, they showed that columns in the primary visual cortex receiving
inputs from the other eye took over the areas that would normally receive
input from the deprived eye. This has important implications for the
understanding of deprivation amblyopia, a type of visual loss due to
unilateral visual deprivation during the so-called critical period. These
kittens also did not develop areas receiving input from both eyes, a feature
needed for binocular vision. Hubel and Wiesel's experiments showed that the
ocular dominance develops irreversibly early in childhood development. These
studies opened the door for the understanding and treatment of childhood
cataracts and strabismus. They were also important in the study of cortical
plasticity.
"Furthermore, the understanding of sensory processing in animals served as
inspiration for the SIFT descriptor (Lowe, 1999), which is a local feature
used in computer vision for tasks such as object recognition and wide-baseline
matching, etc. The SIFT descriptor is arguably the most widely used feature
type for these tasks".
Read previous mail | Read next mail
| |
