Loading in 2 Seconds...
Loading in 2 Seconds...
Itti: CS564 - Brain Theory and Artificial Intelligence University of Southern California. Lecture 28. Overview & Summary Reading Assignment: TMB2 Section 8.3 Supplementary reading: Article on Consciousness in HBTNN. You said “brain” theory??. First step: let’s get oriented!.
Felleman & Van Essen, 1991
Brains, Machines, and
Mathematics, 2nd Edition,
Example of contrast discrimination using yes/no paradigm.
The magnetic properties of blood change with
the amount of oxygenation
resulting in small signal changes
The exclusive source of metabolic energy
of the brain is glycolysis:
+ 6 O2
+ 6 CO2
local susceptibility changes
Gandhi et al., 1999
product of a grating and
equivalent to convolving
input image by sets of
For Further Reading:
Section 5.2 for the VISIONS system for schema-based interpretation of visual scenes.
Visual Schemas in Object Recognition and Scene Analysis
No clear strong input yields
Strongest input is enhanced
and suppresses other inputs
= inhibitory inter-neurons
= copy of input
= receives excitation
from foodness layer
and inhibition from
For all recurrent networks of interest (i.e., neural networks comprised of leaky integrator neurons, and containing loops), giveninitial state and fixed input, there are just three possibilities for the asymptotic state:
The simplest formalization of Hebb’s rule is to increase wij by: wij = k yi xj (1)
fire when it should have fired, and
[Basically B, but with new labels]
- apply weight decay (remember reinforcement learning) during training
- eliminate connections with weight below threshold
- How about eliminating units? For example, eliminate units with total synaptic input weight smaller than threshold.
Filling in the Schemas: Neural Network Models Based on Monkey NeurophysiologyPeter Dominey & Michael Arbib: Cerebral Cortex, 2:153-175 Develop hypotheses onNeural Networksthat yield an equivalent functionality: mappingschemas (functions)to the cooperative cooperation of sets ofbrain regions (structures)
First derivative (gradient)
A cell that is selective for side opposition (Sakata)
Ways to grab this “thing”
“It’s a mug”
AIP extracts the set of affordances for an attended object.These affordances highlight the features of the object relevant to physical interaction with it.
AT: Goodale and Milner: object parameters for grasp (How) but not for saying or pantomiming
DF: Jeannerod et al.: saying and pantomiming (What) but no “How” except for familiar objects with specific sizes.