Drs Nick Hawes (computer sciences) and Jackie Chappell (biosciences) presented on the topic of intelligence and how studies of natural and artificial systems can help each other.
08.10.12 Artificial Intelligence and Cognition - A.I.
1. Natural Cognition and
Artificial Intelligence
What can AI learn from Biology
Nick Hawes
http://www.cs.bham.ac.uk/~nah
2. “It is the science and
engineering of making
intelligent machines,
especially intelligent
computer programs.
It is related to the similar task
of using computers to
understand human
intelligence, but AI does not
have to confine itself to
methods that are
biologically observable.”
John McCarthy
http://www-formal.stanford.edu/jmc/whatisai/
http://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist)
3. “It is the science and
engineering of making
intelligent machines,
especially intelligent
computer programs.
It is related to the similar task
of using computers to
understand human
intelligence, but AI does not
have to confine itself to
methods that are
biologically observable.”
John McCarthy
http://www-formal.stanford.edu/jmc/whatisai/
http://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist)
9. 1254 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 20, NO. 11, NOVEMBER 1998
Short Papers
A Model of Saliency-Based Visual Attention
for Rapid Scene Analysis
Laurent Itti, Christof Koch, and Ernst Niebur
Abstract—A visual attention system, inspired by the behavior and the
neuronal architecture of the early primate visual system, is presented.
Multiscale image features are combined into a single topographical
saliency map. A dynamical neural network then selects attended
locations in order of decreasing saliency. The system breaks down the
complex problem of scene understanding by rapidly selecting, in a
computationally efficient manner, conspicuous locations to be analyzed
in detail.
Index Terms—Visual attention, scene analysis, feature extraction,
target detection, visual search.
———————— F ————————
1 INTRODUCTION
PRIMATES have a remarkable ability to interpret complex scenes in
real time, despite the limited speed of the neuronal hardware avail-
Fig. 1. General architecture of the model.
able for such tasks. Intermediate and higher visual processes appear
to select a subset of the available sensory information before further
processing [1], most likely to reduce the complexity of scene analysis bottom-up saliency and does not require any top-down guidance
[2]. This selection appears to be implemented in the form of a spa- to shift attention. This framework provides a massively parallel
tially circumscribed region of the visual field, the so-called “focus of method for the fast selection of a small number of interesting im-
attention,” which scans the scene both in a rapid, bottom-up, sali- age locations to be analyzed by more complex and time-
ency-driven, and task-independent manner as well as in a slower, consuming object-recognition processes. Extending this approach
top-down, volition-controlled, and task-dependent manner [2]. in “guided-search,” feedback from higher cortical areas (e.g.,
Models of attention include “dynamic routing” models, in knowledge about targets to be found) was used to weight the im-
12. paintin
painting bookcase
g
cabinet
lamp
books
sofa
table
teapot
stand chair
sofa
laptop
table
table
table
chair
chair
birds
cupboard
building
reflectors
banner
microwave globe
street
window lamp
12 street
pipe
lamp
plate bus
bus poster
chair
washing
chair machine people
people
Ales Leonardis, 2012
18. 1646 J.G. Taylor et al. / Image and Vision Computing 27 (2009) 1641–1657
VENTRAL DORSAL
IFG_no_goal
FEF_2_no_goal
IFG
TPJ
SPL
FEF_2
TE
FEF
Object 1 TEO
Space 1
LIP
V4
Object 2
V5
Space 2
V2
V1 V1
(ventral) (dorsal)
Object goal signal
Spatial goal signal
LGN LGN
(ventral) (dorsal)
Fig. 4. The architecture of the hierarchical neural network used in the visual perception/concept simulation in the GNOSYS brain. There is a hierarchy of modules simulating
the known hierarchy of the ventral route of V1 ? V2 ? V4 ? TEO ? TE ? PFC(IFG) in the human brain. The dorsal route is represented by V1 ? V5 ? LIP ? FEF, with a
lateral connectivity from LIP to V4 to allow for linking the spatial position of an object with its identity (as known in the human brain). There are two sets of sigma–pi weights,
one from TPJ in the ventral stream which acts on the inputs from V2 to V4, the other from SPL which acts on the V5 to LIP inputs. This allows for the multiplicative control of
attention.