Deep learning comes of age
5星 · 超过95%的资源 需积分: 10 162 浏览量
2015-05-20
22:21:35
上传
评论 4
收藏 2.93MB PDF 举报 
N
news
june 2013 | vol. 56 | no. 6 | COMMUNICATIONS OF THE ACM 13
Image by heRmaNN cuNtz
Science | DOI:10.1145/2461256.2461262 Gary Anthes
Deep Learning
Comes of Age
Advances on multiple fronts are bringing big improvements to the way
computers learn, increasing the accuracy of speech and vision systems.
I
mprovEmEnts in aLgorithms
and application architectures,
coupled with the recent avail-
ability of very fast computers
and huge datasets, are enabling
major increases in the power of ma-
chine learning systems. In particular,
multilayer artificial neural networks
are producing startling improvements
in the accuracy of computer vision,
speech recognition, and other applica-
tions in a field that has become known
as “deep learning.”
Artificial neural networks (“neural
nets”) are patterned after the arrange-
ment of neurons in the brain, and the
connections, or synapses, between the
neurons. Work on neural nets dates to
the 1960s; although conceptually com-
pelling, they proved difficult to apply
effectively, and they did not begin to
find broad commercial use until the
early 1990s.
Neural nets are systems of highly
interconnected, simple processing el-
ements. The behavior of the net chang-
es according to the “weights” assigned
to each connection, with the output of
any node determined by the weighted
sum of its inputs. The nets do not work
according to hand-coded rules, as
with traditional computer programs;
Rainbow brainwaves made from a computer simulation of pyramidal neurons found in
the cerebral cortex.
资源评论
qq4806061012015-09-25感觉挺有帮助的，下载下来看看
lengwuqin
- 粉丝: 139
- 资源: 333
