Related papers: Adaptive Multi-Scale Goodness Aggregation for Forw…

Unsupervised anomaly detection aims to build models to effectively detect unseen anomalies by only training on the normal data. Although previous reconstruction-based methods have made fruitful progress, their generalization ability is…

Recent Deep Neural Networks (DNN) applications ask for techniques that can explain their behavior. Existing solutions, such as Feature Guided Analysis (FGA), extract rules on their internal behaviors, e.g., by providing explanations related…

This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm…

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs,…

This work focuses on improving the performance and fairness of Federated Learning (FL) in non IID settings by enhancing model aggregation and boosting the training of underperforming clients. We propose FeDABoost, a novel FL framework that…

Precise lesion resection depends on accurately identifying fine-grained anatomical structures. While many coarse-grained segmentation (CGS) methods have been successful in large-scale segmentation (e.g., organs), they fall short in clinical…

The Forward-Forward algorithm eliminates backpropagation's memory constraints and biological implausibility through dual forward passes with positive and negative data. However, conventional implementations suffer from critical inter-layer…

We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but instead of the classical approach of proving convergence…

The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the learning rates for…

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…

The use of semantic segmentation for masking and cropping input images has proven to be a significant aid in medical imaging classification tasks by decreasing the noise and variance of the training dataset. However, implementing this…

To address the challenges posed by the heterogeneity inherent in federated learning (FL) and to attract high-quality clients, various incentive mechanisms have been employed. However, existing incentive mechanisms are typically utilized in…

Recently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a…

Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory…

The Forward-Forward (FF) algorithm was recently proposed as a local learning method to address the limitations of backpropagation (BP), offering biological plausibility along with memory-efficient and highly parallelized computational…

The so-called Forward-Forward Algorithm (FFA) has recently gained momentum as an alternative to the conventional back-propagation algorithm for neural network learning, yielding competitive performance across various modeling tasks. By…

In this paper, we introduce an Adaptive Graph Signal Processing with Dynamic Semantic Alignment (AGSP DSA) framework to perform robust multimodal data fusion over heterogeneous sources, including text, audio, and images. The requested…

Micro-expressions are typically regarded as unconscious manifestations of a person's genuine emotions. However, their short duration and subtle signals pose significant challenges for downstream recognition. We propose a multi-task learning…

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

This thesis presents a novel approach to neural network training that addresses the challenge of determining the optimal number of learning factors. The proposed Adaptive Multiple Optimal Learning Factors (AMOLF) algorithm dynamically…