predictive sequence learning with spiking neurons using rank

De : "Joy Bose" joyboseroy [ � ] gmail.com

Dear connectionists,

This is to announce that my PhD dissertation on the topic of sequence
learning is available for download.

Title: Engineering a sequence machine out of spiking neurons
employing rank order codes

Download URL: http://www.cs.man.ac.uk/~bosej/JoyBose_PhD.pdf (216
pages, 5.23 MB)

With regards,
Joy Bose
APT Research Group
Computer Science
The University of Manchester
Email: bosejATcs.man.ac.uk, joyboseroyATgmail.com
------------------------------------------------------------------------
------------------------------------------------------------------------
--------------------------
Abstract:
Sequence memories play an important role in biological systems. For
example, the mammalian brain continuously processes, learns and
predicts spatio-temporal sequences of sensory inputs. The work
described in this dissertation demonstrates how a sequence memory may
be built from biologically plausible spiking neural components. The
memory is incorporated in a sequence machine, an automaton that can
perform on-line learning and prediction of sequences of symbols.

The sequence machine comprises an associative memory which is a
variant of Pentti Kanerva's Sparse Distributed Memory, together with
a separate memory for storing the sequence context or history. The
associative memory has at its core a scalable correlation matrix
memory employing a localised learning rule which can be implemented
with spiking neurons.

The symbols constituting a sequence are encoded as rank-ordered N-of-
M codes, each code being implemented as a burst of spikes emitted by
a layer of neurons. When appropriate neural structures are used the
spike bursts maintain coherence and stability as they pass through
successive neural layers. The system is modelled using a
representation of order that abstracts time, and the abstracted
system is shown to perform equivalently to a low-level spiking neural
system. The spiking neural implementation of the sequence memory
model highlights issues that arise when engineering high-level
systems with asynchronous spiking neurons as building blocks.

Finally, the sequence learning framework is used to simulate
different sequence machine models. The new model proposed here is
tested under varied parameters to characterise its performance in
terms of the accuracy of its sequence predictions.