Reservoirs learn to learn
The common procedure in reservoir computing is to take a "found" reservoir,
such as a recurrent neural network with randomly chosen synaptic weights or a
complex physical device, and to adapt the weights of linear readouts from
this reservoir for a particular computing task. We address the question of
whether the performance of reservoir computing can be significantly enhanced
if one instead optimizes some (hyper)parameters of the reservoir, not for a
single task but for the range of all possible tasks in which one is
potentially interested, before the weights of linear readouts are optimized
for a particular computing task. After all, networks of neurons in the brain
are also known to be not randomly connected. Rather, their structure and
parameters emerge from complex evolutionary and developmental processes,
arguably in a way that enhances speed and accuracy of subsequent learning of
any concrete task that is likely to be essential for the survival of the
organism. We apply the Learning-to-Learn (L2L) paradigm to mimick this
two-tier process, where a set of (hyper)parameters of the reservoir are
optimized for a whole family of learning tasks. We found that this
substantially enhances the performance of reservoir computing for the
families of tasks that we considered. Furthermore, L2L enables a new form of
reservoir learning that tends to enable even faster learning, where not even
the weights of readouts need to be adjusted for learning a concrete task. We
present demos and performance results of these new forms of reservoir
computing for reservoirs that consist of networks of spiking neurons, and are
hence of particular interest from the perspective of neuroscience and
implementations in spike-based neuromorphic hardware. We leave it as an open
question what performance advantage the new methods that we propose provide
for other types of reservoirs.
Reference: A. Subramoney, F. Scherr, and W. Maass.
Reservoirs learn to learn.
In K. Nakajima and I. Fischer, editors, Reservoir Computing: Theory,
Physical Implementations, and Applications. Springer, 2020.