Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal

A new framework called NITRO-D has been introduced for training deep convolutional neural networks (CNNs) using only integer operations, addressing the limitations of existing methods that rely on floating-point arithmetic. This advancement allows for both training and inference in environments where floating-point operations are unavailable, enhancing the applicability of deep learning models in resource-constrained settings.

Recent research highlights a paradox in deep learning, revealing that adversarially trained models, designed to enhance robustness against attacks, may inadvertently increase the transferability of adversarial examples. This study involved training 36 diverse models, including CNNs and ViTs, and conducting extensive transferability experiments, leading to significant findings about model vulnerabilities.

A recent study has introduced a hierarchical attention model for detecting sparse volumetric anomalies in subclinical keratoconus using 3D anterior segment OCT volumes. This model was compared against sixteen modern deep learning architectures, revealing superior performance in sensitivity and specificity over traditional 2D/3D CNNs and ViTs.

A novel approach to image classification has been introduced, leveraging higher-order convolutions inspired by biological visual processing. This method enhances classical convolutional neural networks (CNNs) by incorporating learnable convolutions that capture complex interactions, demonstrating superior performance on various datasets including MNIST and CIFAR-10.