Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical analysis demonstrating that the structure of a deep neural network (DNN) can condition the model to assign all predictions to the same class, even before the beginning of training, and in the absence of explicit biases. We prove that, besides dataset properties, the presence of this phenomenon, which we call \textit{Initial Guessing Bias} (IGB), is influenced by model choices including dataset preprocessing methods, and architectural decisions, such as activation functions, max-pooling layers, and network depth. Our analysis of IGB provides information for architecture selection and model initialization. We also highlight theoretical consequences, such as the breakdown of node-permutation symmetry, the violation of self-averaging and the non-trivial effects that depth has on the phenomenon.

翻译：理解和控制神经网络中的偏差效应对于确保模型性能的准确性和公平性至关重要。在分类问题的背景下，我们通过理论分析证明，深度神经网络（DNN）的结构能够使模型将所有预测分配给同一类别，甚至在训练开始之前且不存在显式偏差的情况下即是如此。我们证明，除了数据集属性外，这种我们称之为\textit{初始猜测偏差}（IGB）的现象的存在，还受到模型选择的影响，包括数据预处理方法以及架构决策，如激活函数、最大池化层和网络深度。我们对IGB的分析为架构选择和模型初始化提供了参考依据。我们还强调了其理论影响，例如节点置换对称性的破坏、自平均性的违反以及深度对该现象产生的非平凡效应。