arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.08322cs.LGcs.AI
收藏

不同损失函数的鲁棒性及其对网络学习能力的影响

Robustness of different loss functions and their impact on networks learning capability

KU Leuven(鲁汶大学)

Vishal Rajput

摘要:

人工智能的最新发展使其无处不在,每个行业都在试图采用某种形式的智能数据处理。尽管在该领域取得了如此多的进展,但人工智能的全部能力还有待业界开发。涉及一些风险因素的行业仍然对人工智能的使用持谨慎态度,因为对这种自主系统缺乏信任。今天的人工智能可能在很多事情上都很好,但在推理方面却很糟糕,人工智能的这种行为可能会导致灾难性的结果。自动驾驶汽车撞到人或无人机卡在树上是人工智能决策导致灾难性结果的几个例子。为了深入了解并解释人工智能的学习能力,我们将尝试分析损失函数的工作原理。对于我们的情况,我们将使用两组损失函数,广义损失函数如二进制交叉熵或BCE和专用损失函数如骰子损失或焦点损失。通过一系列的实验,我们将确定组合不同的损失函数是否比使用单个损失函数更好,如果是,那么背后的原因是什么。为了确定广义损失和特殊损失之间的差异,我们将使用上述损失训练几个模型,然后比较它们在对抗性示例上的鲁棒性。特别是,我们将研究当我们改变与最显著梯度对应的像素时,不同模型的准确性下降的速度。

英文摘要:

Recent developments in AI have made it ubiquitous, every industry is trying to adopt some form of intelligent processing of their data. Despite so many advances in the field, AIs full capability is yet to be exploited by the industry. Industries that involve some risk factors still remain cautious about the usage of AI due to the lack of trust in such autonomous systems. Present-day AI might be very good in a lot of things but it is very bad in reasoning and this behavior of AI can lead to catastrophic results. Autonomous cars crashing into a person or a drone getting stuck in a tree are a few examples where AI decisions lead to catastrophic results. To develop insight and generate an explanation about the learning capability of AI, we will try to analyze the working of loss functions. For our case, we will use two sets of loss functions, generalized loss functions like Binary cross-entropy or BCE and specialized loss functions like Dice loss or focal loss. Through a series of experiments, we will establish whether combining different loss functions is better than using a single loss function and if yes, then what is the reason behind it. In order to establish the difference between generalized loss and specialized losses, we will train several models using the above-mentioned losses and then compare their robustness on adversarial examples. In particular, we will look at how fast the accuracy of different models decreases when we change the pixels corresponding to the most salient gradients.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑