Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of tasks in computer vision. However, we argue that biases can be disregarded for some image-related tasks such as image classification, by considering the intrinsic distribution of images in the input space and desired model properties from first principles. Our findings suggest that zero-bias neural networks can perform comparably to biased networks for practical image classification tasks. We demonstrate that zero-bias neural networks possess a valuable property called scalar (multiplication) invariance. This means that the prediction of the network remains unchanged when the contrast of the input image is altered. We extend scalar invariance to more general cases, enabling formal verification of certain convex regions of the input space. Additionally, we prove that zero-bias neural networks are fair in predicting the zero image. Unlike state-of-the-art models that may exhibit bias toward certain labels, zero-bias networks have uniform belief in all labels. We believe dropping bias terms can be considered as a geometric prior in designing neural network architecture for image classification, which shares the spirit of adapting convolutions as the transnational invariance prior. The robustness and fairness advantages of zero-bias neural networks may also indicate a promising path towards trustworthy and ethical AI.

翻译：如同权重参数一样，偏置项也是许多流行机器学习模型（包括神经网络）的可学习参数。人们认为偏置能够增强神经网络的表示能力，使其能够解决计算机视觉中的各类任务。然而，我们认为，通过从第一性原理出发考虑输入空间中图像的内在分布及期望的模型性质，对于图像分类等某些图像相关任务，偏置项可以被忽略。我们的研究结果表明，在实际图像分类任务中，零偏置神经网络的性能可与带偏置网络相当。我们证明零偏置神经网络具有一种名为标量乘性不变性的宝贵性质。这意味着当输入图像的对比度改变时，网络的预测保持不变。我们将这种标量不变性推广到更一般的情况，从而能够对输入空间的某些凸区域进行形式化验证。此外，我们证明零偏置神经网络在预测全零图像时是公平的。与可能对特定标签表现出偏置的现有先进模型不同，零偏置网络对所有标签具有均等的置信度。我们认为，在针对图像分类设计神经网络架构时，丢弃偏置项可被视为一种几何先验，这与采用卷积作为平移不变性先验的精神一脉相承。零偏置神经网络的鲁棒性和公平性优势，还可能为通往可信与合乎伦理的人工智能预示一条有前景的道路。