The perceptual loss has been widely used as an effective loss term in image synthesis tasks
including image super-resolution [16], and style transfer [14]. It was believed that the …

Neural networks trained on visual data are well-known to be vulnerable to often
imperceptible adversarial perturbations. The reasons for this vulnerability are still being …

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible
changes to the input images. To address this vulnerability, adversarial training creates …

Traffic congestion in urban areas presents significant challenges, and Intelligent
Transportation Systems (ITS) have sought to address these via automated and adaptive …

Transformer based large language models with emergent capabilities are becoming
increasingly ubiquitous in society. However, the task of understanding and interpreting their …

To account for the explanatory role representations play in cognitive science, Egan's
deflationary account introduces a distinction between cognitive and mathematical contents …

Albeit displaying remarkable performance across a range of tasks, Deep Neural Networks
(DNNs) are highly vulnerable to adversarial examples which are carefully created to deceive …

Plant diseases devastatingly reduce the potential crop yield by an average of 40%, and up
to 100% in the developing world. The detection of plant diseases remains difficult due to the …

In the previous lecture, we talked about adversarial examples—both targeted and non-
targeted—and learned how to compute them to attack a model. We also learned about …

Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is
believed that by processing augmented inputs in tandem with the original ones, the model …