We introduce a two-stage multitask learning framework for analyzing Electroencephalography (EEG) signals that integrates denoising, dynamical modeling, and representation learning. In the first stage, a denoising autoencoder is trained to suppress artifacts and stabilize temporal dynamics, providing robust signal representations. In the second stage, a multitask architecture processes these denoised signals to achieve three objectives: motor imagery classification, chaotic versus non-chaotic regime discrimination using Lyapunov exponent-based labels, and self-supervised contrastive representation learning with NT-Xent loss. A convolutional backbone […]

Ver mais

arXiv:2602.21259v1 Announce Type: new Abstract: Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs) have emerged as platforms capable of operating in both aerial and underwater environments, enabling applications such as inspection, mapping, search, and rescue in challenging scenarios. However, the development of novel methodologies poses significant challenges due to the distinct dynamics and constraints of the air and water domains. In this work, we present persistent monitoring tasks for HUAUVs by combining Deep Reinforcement Learning (DRL) and Transfer Learning to […]

Ver mais

arXiv:2607.05546v1 Announce Type: new Abstract: We develop a unified function space theory of deep fully connected neural networks. Functions in our spaces are defined recursively as $ell^1$-bounded linear combinations of activated functions from preceding layers, with a dictionary of affine functions at the first layer. Unlike existing theories that are largely specialized to homogeneous activations such as the ReLU, our framework provides a meaningful notion of functional complexity for deep networks with a broad range of homogeneous and […]

Ver mais

arXiv:2602.09146v1 Announce Type: new Abstract: Retrieving videos based on semantic motion is a fundamental, yet unsolved, problem. Existing video representation approaches overly rely on static appearance and scene context rather than motion dynamics, a bias inherited from their training data and objectives. Conversely, traditional motion-centric inputs like optical flow lack the semantic grounding needed to understand high-level motion. To demonstrate this inherent bias, we introduce the SimMotion benchmarks, combining controlled synthetic data with a new human-annotated real-world dataset. […]

Ver mais

According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recent works provide a formalization of this phenomenon when learning multi-index models. In this setting, we are given $n$ i.i.d. pairs $({boldsymbol x}_i,y_i)$, where the covariate vectors ${boldsymbol x}_iinmathbb{R}^d$ are isotropic, and responses $y_i$ only depend on ${boldsymbol x}_i$ through a $k$-dimensional projection ${boldsymbol Θ}_*^{sf T}{boldsymbol x}_i$. Feature learning amounts to learning the latent […]

Ver mais

arXiv:2601.22256v1 Announce Type: new Abstract: Monitoring in-class programming exercises can help instructors identify struggling students and common challenges. However, understanding students’ progress can be prohibitively difficult, particularly for multi-faceted problems that include multiple steps with complex interdependencies, have no predictable completion order, or involve evaluation criteria that are difficult to summarize across many students (e.g., exercises building interactive web-based user interfaces). We introduce SPARK, a coding exercise monitoring dashboard designed to address these challenges. SPARK allows instructors to […]

Ver mais