Hair artifacts in dermoscopic images present significant challenges for accurate skin lesion analysis, potentially obscuring critical diagnostic features in dermatological assessments. This work introduces a fine-tuned SegFormer model augmented with dropout regularization to achieve precise hair mask segmentation. The proposed SegformerWithDropout architecture leverages the MiT-B2 encoder, pretrained on ImageNet, with an in-channel count of 3 and 2 output classes, incorporating a dropout probability of 0.3 in the segmentation head to prevent overfitting. Training is conducted on a specialized dataset of 500 dermoscopic skin lesion images with fine-grained hair mask annotations, employing 10-fold cross-validation, AdamW optimization with a learning rate of 0.001, and cross-entropy loss. Early stopping is applied based on validation loss, with a patience of 3 epochs and a maximum of 20 epochs per fold. Performance is evaluated using a comprehensive suite of metrics, including Intersection over Union (IoU), Dice coefficient, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). Experimental results from the cross-validation demonstrate robust performance, with average Dice coefficients reaching approximately 0.96 and IoU values of 0.93, alongside favorable PSNR (around 34 dB), SSIM (0.97), and low LPIPS (0.06), highlighting the model's effectiveness in accurate hair artifact segmentation and its potential to enhance preprocessing for downstream skin cancer detection tasks.

The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), enabling performance across diverse tasks with little task-specific training. However, LLMs remain susceptible to social biases, particularly reflecting harmful stereotypes from training data, which can disproportionately affect marginalised communities. We measure gender bias in Maltese LMs, arguing that such bias is harmful as it reinforces societal stereotypes and fails to account for gender diversity, which is especially problematic in gendered, low-resource languages. While bias evaluation and mitigation efforts have progressed for English-centric models, research on low-resourced and morphologically rich languages remains limited. This research investigates the transferability of debiasing methods to Maltese language models, focusing on BERTu and mBERTu, BERT-based monolingual and multilingual models respectively. Bias measurement and mitigation techniques from English are adapted to Maltese, using benchmarks such as CrowS-Pairs and SEAT, alongside debiasing methods Counterfactual Data Augmentation, Dropout Regularization, Auto-Debias, and GuiDebias. We also contribute to future work in the study of gender bias in Maltese by creating evaluation datasets. Our findings highlight the challenges of applying existing bias mitigation methods to linguistically complex languages, underscoring the need for more inclusive approaches in the development of multilingual NLP.

Dropout regularization methods prune a neural network's pre-determined backbone structure to avoid overfitting. However, a deep model still tends to be poorly calibrated with high confidence on incorrect predictions. We propose a unified Bayesian model selection method to jointly infer the most plausible network depth warranted by data, and perform dropout regularization simultaneously. In particular, to infer network depth we define a beta process over the number of hidden layers which allows it to go to infinity. Layer-wise activation probabilities induced by the beta process modulate neuron activation via binary vectors of a conjugate Bernoulli process. Experiments across domains show that by adapting network depth and dropout regularization to data, our method achieves superior performance comparing to state-of-the-art methods with well-calibrated uncertainty estimates. In continual learning, our method enables neural networks to dynamically evolve their depths to accommodate incrementally available data beyond their initial structures, and alleviate catastrophic forgetting.

Modern neural networks often activate all neurons for every input, leading to unnecessary computation and inefficiency. We introduce Matrix-Interpolated Dropout Layer (MID-L), a novel module that dynamically selects and activates only the most informative neurons by interpolating between two transformation paths via a learned, input-dependent gating vector. Unlike conventional dropout or static sparsity methods, MID-L employs a differentiable Top-k masking strategy, enabling per-input adaptive computation while maintaining end-to-end differentiability. MID-L is model-agnostic and integrates seamlessly into existing architectures. Extensive experiments on six benchmarks, including MNIST, CIFAR-10, CIFAR-100, SVHN, UCI Adult, and IMDB, show that MID-L achieves up to average 55\% reduction in active neurons, 1.7$\times$ FLOPs savings, and maintains or exceeds baseline accuracy. We further validate the informativeness and selectivity of the learned neurons via Sliced Mutual Information (SMI) and observe improved robustness under overfitting and noisy data conditions. Additionally, MID-L demonstrates favorable inference latency and memory usage profiles, making it suitable for both research exploration and deployment on compute-constrained systems. These results position MID-L as a general-purpose, plug-and-play dynamic computation layer, bridging the gap between dropout regularization and efficient inference.

Neural network language models (LMs) are confronted with significant challenges in generalization and robustness. Currently, many studies focus on improving either generalization or robustness in isolation, without methods addressing both aspects simultaneously, which presents a significant challenge in developing LMs that are both robust and generalized. In this paper, we propose a bi-stage optimization framework to uniformly enhance both the generalization and robustness of LMs, termed UEGR. Specifically, during the forward propagation stage, we enrich the output probability distributions of adversarial samples by adaptive dropout to generate diverse sub models, and incorporate JS divergence and adversarial losses of these output distributions to reinforce output stability. During backward propagation stage, we compute parameter saliency scores and selectively update only the most critical parameters to minimize unnecessary deviations and consolidate the model's resilience. Theoretical analysis shows that our framework includes gradient regularization to limit the model's sensitivity to input perturbations and selective parameter updates to flatten the loss landscape, thus improving both generalization and robustness. The experimental results show that our method significantly improves the generalization and robustness of LMs compared to other existing methods across 13 publicly available language datasets, achieving state-of-the-art (SOTA) performance.

Image classification is a fundamental task in computer vision with diverse applications, ranging from autonomous systems to medical imaging. The CIFAR-10 dataset is a widely used benchmark to evaluate the performance of classification models on small-scale, multi-class datasets. Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art results; however, they often suffer from overfitting and suboptimal feature representation when applied to challenging datasets like CIFAR-10. In this paper, we propose an enhanced CNN architecture that integrates deeper convolutional blocks, batch normalization, and dropout regularization to achieve superior performance. The proposed model achieves a test accuracy of 84.95%, outperforming baseline CNN architectures. Through detailed ablation studies, we demonstrate the effectiveness of the enhancements and analyze the hierarchical feature representations. This work highlights the potential of refined CNN architectures for tackling small-scale image classification problems effectively.

In the study of neural network interpretability, there is growing evidence to suggest that relevant features are encoded across many neurons in a distributed fashion. Making sense of these distributed representations without knowledge of the network's encoding strategy is a combinatorial task that is not guaranteed to be tractable. This work explores one feasible path to both detecting and tracing the joint influence of neurons in a distributed representation. We term this approach Activation Spectroscopy (ActSpec), owing to its analysis of the pseudo-Boolean Fourier spectrum defined over the activation patterns of a network layer. The sub-network defined between a given layer and an output logit is cast as a special class of pseudo-Boolean function. The contributions of each subset of neurons in the specified layer can be quantified through the function's Fourier coefficients. We propose a combinatorial optimization procedure to search for Fourier coefficients that are simultaneously high-valued, and non-redundant. This procedure can be viewed as an extension of the Goldreich-Levin algorithm which incorporates additional problem-specific constraints. The resulting coefficients specify a collection of subsets, which are used to test the degree to which a representation is distributed. We verify our approach in a number of synthetic settings and compare against existing interpretability benchmarks. We conclude with a number of experimental evaluations on an MNIST classifier, and a transformer-based network for sentiment analysis.

Even though dropout is a popular regularization technique, its theoretical properties are not fully understood. In this paper we study dropout regularization in extended generalized linear models based on double exponential families, for which the dispersion parameter can vary with the features. A theoretical analysis shows that dropout regularization prefers rare but important features in both the mean and dispersion, generalizing an earlier result for conventional generalized linear models. Training is performed using stochastic gradient descent with adaptive learning rate. To illustrate, we apply dropout to adaptive smoothing with B-splines, where both the mean and dispersion parameters are modelled flexibly. The important B-spline basis functions can be thought of as rare features, and we confirm in experiments that dropout is an effective form of regularization for mean and dispersion parameters that improves on a penalized maximum likelihood approach with an explicit smoothness penalty.

Dropout is a simple and powerful regularization technique for neural networks and deep learning models. In this post, you will discover the Dropout regularization technique and how to apply it to your models in PyTorch models. Dropout is a regularization technique for neural network models proposed around 2012 to 2014. It is a layer in the neural network. During training of a neural network model, it will take the output from its previous layer, randomly select some of the neurons and zero them out before passing to the next layer, effectively ignored them. This means that their contribution to the activation of downstream neurons is temporally removed on the forward pass, and any weight updates are not applied to the neuron on the backward pass.