# Exploring weight initialization, diversity of solutions, and degradation in recurrent neural networks trained for temporal and decision-making tasks

## TL;DR

This study investigates how recurrent neural networks trained on temporal tasks exhibit diverse dynamics, degrade gracefully under various conditions, and how their robustness can be characterized, providing insights into modeling brain functions.

## Contribution

The paper introduces a framework for analyzing RNN dynamics and robustness, highlighting the diversity of solutions and degradation patterns in models of brain-like temporal processing.

## Key findings

- Different RNNs solve the same task with distinct dynamics.
- Performance degrades gracefully with reduced network size, increased interval duration, or connectivity damage.
- The framework aids in quantifying model robustness and diversity in computational neuroscience.

## Abstract

Recurrent Neural Networks (RNNs) are frequently used to model aspects of brain function and structure. In this work, we trained small fully-connected RNNs to perform temporal and flow control tasks with time-varying stimuli. Our results show that different RNNs can solve the same task by converging to different underlying dynamics and also how the performance gracefully degrades as either network size is decreased, interval duration is increased, or connectivity damage is increased. For the considered tasks, we explored how robust the network obtained after training can be according to task parameterization. In the process, we developed a framework that can be useful to parameterize other tasks of interest in computational neuroscience. Our results are useful to quantify different aspects of the models, which are normally used as black boxes and need to be understood in order to model the biological response of cerebral cortex areas.