Dynamic Feedforward and Recurrent Networks

(

**Jürgen
Schmidhuber ^{1}, TUM **

Most known learning algorithms for dynamic neural networks in
non-stationary environments need global computations to
perform credit assignment. These algorithms
either are not local in time or
not local in space. Those algorithms which are local in both
time and space usually can not deal sensibly with `hidden units'.
In contrast, as far as we can judge
by now, learning rules in biological systems with many `hidden
units' are local in both space and time.
In this paper we propose a parallel on-line learning algorithm which
performs local computations only, yet still is designed to deal with
hidden units and with units whose past activations are
`hidden in time'.
The approach is inspired by Holland's idea of the bucket
brigade for classifier systems, which is transformed to run on
a neural network
with fixed topology. The result is a feedforward or
recurrent `neural'
dissipative system which is
consuming `weight-substance' and permanently trying to distribute this
substance onto its connections in an appropriate way. Simple
experiments demonstrating the feasability of the algorithm
are reported.

*Keywords:* recurrent networks, credit assignment,
local computations,
dissipative systems,
internal feedback, external feedback,
neural bucket brigade.

- Introduction
- Classifier Systems and the Bucket Brigade.
- The Neural Bucket Brigade (NBB)

- Simple Experiments
- Conclusion
- Bibliography
- About this document ...

Back to Reinforcement Learning Economy page

Back to Recurrent Neural Networks page