A Gradient Descent Method for a Neural

| It has been demonstrated that higher order recurrent neu-ral networks exhibit an underlying fractal attractor as an artifact of their dynamics. These fractal attractors ooer a very eecent mechanism to encode visual memories in a neu-ral substrate, since even a simple twelve weight network can encode a very large set of diierent images. The main problem in this memory model, which so far has remained unaddressed, is how to train the networks to learn these diierent attractors. Following other neural training methods this paper proposes a Gradient Descent method to learn the attractors. The method is based on an error function which examines the eeects of the current network transform on the desired fractal attractor. It is tested across a bank of diierent target fractal attractors and at diierent noise levels. The results show positive performance across three error measures.