Nurani Rajagopal Rohan

arXiv2026

Chaotic Oscillatory Associative Memory

Associative memory models retrieve stored information through content-based addressing, mimicking the neural processes of animal brains. The classical Hopfield network-based models store memories as vectors of discrete values and have good storage capacity but do not consider the role of neuronal synchronization in memory storage and retrieval as observed in brains. This is addressed in phase-oscillator-based models which store memories as time-dependent phase-synchronized states, but suffer from instability and low capacity. The present study addresses these challenges through a novel chaotic oscillator-based associative memory model, by defining a phase relationship in chaotic systems and encoding memory as synchronized states of these phases. The underlying chaos in the network is shown to significantly improve both storage and retrieval and offer insights into the dynamics of memory retrieval.

q-bio.NC↗

arXiv2024

Deep Oscillatory Neural Network

We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscillatory activity. With this motivation, the DONN is designed to have oscillatory internal dynamics. Neurons of the DONN are either nonlinear neural oscillators or traditional neurons with sigmoidal or ReLU activation. The neural oscillator used in the model is the Hopf oscillator, with the dynamics described in the complex domain. Input can be presented to the neural oscillator in three possible modes. The sigmoid and ReLU neurons also use complex-valued extensions. All the weight stages are also complex-valued. Training follows the general principle of weight change by minimizing the output error and therefore has an overall resemblance to complex backpropagation. A generalization of DONN to convolutional networks known as the Oscillatory Convolutional Neural Network is also proposed. The two proposed oscillatory networks are applied to a variety of benchmark problems in signal and image/video processing. The performance of the proposed models is either comparable or superior to published results on the same data sets.

cs.NE↗