Emergent Granger Causality in Neural Networks: Can Prediction Alone Reveal Structure?

A recent study published on arXiv introduces a distribution-based framework aimed at mitigating individual skin tone bias in skin lesion classification, emphasizing the importance of treating skin tone as a continuous attribute. The research employs kernel density estimation to model skin tone distributions and proposes a distance-based reweighting loss function to address underrepresentation of minority tones.

A recent study investigates the expressivity of one-dimensional ReLU deep neural networks (DNNs), revealing that the expected number of linear regions increases with the number of neurons in hidden layers. This research provides insights into the structure and capabilities of these networks, particularly in the infinite-width limit.

A new study introduces a data-driven ensemble approach to enhance transparency and stability in bilateral teleoperation systems, addressing challenges posed by communication delays. The framework replaces traditional wave-variable methods with advanced sequence models, including LSTM and CNN-LSTM, optimized through the Optuna algorithm. Experimental validation was conducted using Python, demonstrating the effectiveness of this innovative approach.

A recent study has transformed extensive Swedish register data into textual life trajectories to predict residential mobility, utilizing data from 6.9 million individuals between 2001 and 2013. By converting demographic and life changes into semantically rich texts, the research employs various NLP architectures, including LSTM and BERT, to enhance prediction accuracy for residential moves from 2013 to 2017.

PRISM has been introduced as a lightweight fully convolutional classifier for multivariate time series classification, utilizing symmetric multi-resolution convolutional layers to efficiently capture both short-term patterns and longer-range dependencies. This model significantly reduces the number of learnable parameters while maintaining performance across various benchmarks, including human activity recognition and sleep state detection.

A recent study on monocular depth estimation highlights the disparity between model accuracy and human-like perception, particularly in applications such as autonomous driving and robotics. Researchers evaluated 69 monocular depth estimators using the KITTI dataset, revealing that high accuracy does not necessarily correlate with human-like behavior in depth perception.

A novel deep hybrid segmentation framework named Residual-SwinCA-Net has been proposed for malignant lesion segmentation in breast ultrasound images, utilizing a combination of residual CNN modules and customized Swin Transformer blocks to enhance feature extraction and gradient stability. The framework also incorporates advanced techniques for noise suppression and boundary preservation to improve segmentation accuracy.

A recent study introduces a hybrid model for stock market forecasting that integrates news sentiment and time series data using Graph Neural Networks (GNNs). This approach contrasts with traditional models that primarily rely on historical price data, aiming to enhance prediction accuracy by incorporating external signals from financial news articles. The GNN model was evaluated against a baseline Long Short-Term Memory (LSTM) model, demonstrating superior performance in predicting stock price movements.