Biological neuronal networks (BNNs) constitute a niche for inspiration and analogy making for researchers that focus on artificial neuronal networks (ANNs). Moreover, neuroscientists increasingly use ANNs as a model for the brain. However, apart from certain similarities and analogies that can be drawn between ANNs and BNNs, such networks exhibit marked differences, specifically with respect to their network topology. Here, we investigate to what extent network topology found in nature can lead to beneficial aspects in recurrent neural networks (RNNs): i) the prediction performance itself, that is, the capacity of the network to minimize the desired function at hand in test data and ii) speed of training, that is, how fast during training the network reaches its optimal performance. To this end, we examine different ways to construct RNNs that instantiate the network topology of brains of different species. We refer to such RNNs as bio-instantiated. We examine the bio-instantiated RNNs in the context of a key cognitive capacity, that is, working memory, defined as the ability to track task-relevant information as a sequence of events unfolds in time. We highlight what strategies can be used to construct RNNs with the network topology found in nature, without sacrificing prediction capacity and speed of training. Despite that we observe no enhancement of performance when compared to randomly wired RNNs, our approach demonstrates how empirical neural network data can be used for constructing RNNs, thus, facilitating further experimentation with biologically realistic networks topology.
bioRxiv Subject Collection: Neuroscience