Biomedical Engineering Reference
In-Depth Information
17.6
Motor learning paradigms
17.6.1
Learning paradigms in neural networks
At the core of the theories of neural network models is the attempt to capture gen-
eral approaches for learning from experience procedures that are too complex to be
expressed by means of explicit or symbolic models [2]. The mechanism of learning
and memory has been an intriguing question after the establishment of the neuron
theory at the turn of the 19th century [57] and the ensuing conjectures that memo-
ries are encoded at synaptic sites [26] as a consequence of a process of learning. In
accordance with this prediction, synaptic plasticity was first discovered in the hip-
pocampus and nowadays it is generally thought that LPT (long term potentiation) is
the basis of cognitive learning and memory, although the specific mechanisms are
still a matter of investigation.
Three main paradigms for training the parameters or
synaptic weights
of neural
network models have been identified:
1.
Supervised learning,
in which a teacher or supervisor provides a detailed de-
scription of the desired response for any given stimulus and exploits the mis-
match between the computed and the desired response or error signal for mod-
ifying the synaptic weights according to an iterative procedure. The math-
ematical technique typically used in this type of learning is known as
back
propagation
and is based on a gradient-descent mechanism that attempts to
minimize the average output error;
2.
Reinforcement learning
, which also assumes the presence of a
supervisor
or
teacher but its intervention is only supposed to reward (or punish) the degree
of success of a given control pattern, without any detailed input-output instruc-
tion. The underlying mathematical formulation is aimed at the maximization
of the accumulated reward during the learning period;
3.
Unsupervised learning,
in which there is no teacher or explicit instruction and
the network is only supposed to capture the statistical structure of the input
stimuli in order to build a consistent but concise internal representation of the
input. The typical learning strategy is called Hebbian, in recognition of the pi-
oneering work of D.O. Hebb, and is based on a
competitive
or
self-organising
mechanism that uses the local correlation in the activity of adjacent neurons
and aims at the maximization of the mutual information between stimuli and
internal patterns.
17.6.2
Adaptive behaviour and motor learning
The neural machinery for learning and producing adaptive behaviours in vertebrates
is sketched in
Figure 17.18
,
which emphasizes the recurrent, non-hierarchical flow
Search WWH ::
Custom Search