arXiv:2602.07200v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as information is transmitted through temporal spiking patterns. The core element of an SNN is the spiking neuron, which converts input data into spikes following the Leaky Integrate-and-Fire (LIF) neuron model. This model includes several important hyperparameters, such as the membrane potential threshold and membrane time constant. Both the DNNs and SNNs have proven to be exploitable […]

Ver mais

arXiv:2602.17826v1 Announce Type: new Abstract: Language models exhibit fundamental limitations — hallucination, brittleness, and lack of formal grounding — that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with […]

Ver mais

arXiv:2601.03392v1 Announce Type: new Abstract: Feedforward artificial neural networks (ANNs) trained on static images remain the dominant models of the the primate ventral visual stream, yet they are intrinsically limited to static computations. The primate world is dynamic, and the macaque ventral visual pathways, specifically the inferior temporal (IT) cortex not only supports object recognition but also encodes object motion velocity during naturalistic video viewing. Does IT’s temporal responses reflect nothing more than time-unfolded feedforward transformations, framewise features […]

Ver mais

Continual learning in Large Language Models (LLMs) faces the critical challenge of balancing stability (retaining old knowledge) and plasticity (learning new tasks). While Experience Replay (ER) is a standard countermeasure against catastrophic forgetting, its impact across diverse capabilities remains underexplored. In this work, we uncover a critical dichotomy in ER’s behavior: while it induces positive backward transfer on robust, unstructured tasks (e.g., boosting performance on previous NLP classification tasks through repeated rehearsal), it causes severe negative transfer on […]

Ver mais

We show that the expected computational complexity of the Junction-Tree Algorithm for maximum a posteriori inference in graphical models can be improved. Our results apply whenever the potentials over maximal cliques of the triangulated graph are factored over subcliques. This is common in many real applications, as we illustrate with several examples. The new algorithms are easily implemented, and experiments show substantial speed-ups over the classical Junction-Tree Algorithm. This enlarges the class of models for which exact inference […]

Ver mais

arXiv:2601.03220v1 Announce Type: cross Abstract: Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated without considering a downstream task? On these questions, Shannon information and Kolmogorov complexity come up nearly empty-handed, in part because they assume observers with unlimited computational capacity and fail to target the useful information content. In this […]

Ver mais

arXiv:2601.19912v1 Announce Type: new Abstract: Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors. While prior work has examined GPU reliability, most studies have focused on general-purpose applications or conventional neural networks mostly used for vision tasks such as classification and detection. In contrast, systematic analysis […]

Ver mais

Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent representations. NPE employs one or more Prior Estimation Modules trained jointly with the backbone via a one-way logistic loss. Under the Neural Collapse regime, NPE is analytically shown to recover the class log-prior up to an additive constant, providing a theoretically grounded adaptive signal without […]

Ver mais

arXiv:2601.05065v1 Announce Type: cross Abstract: A key challenge in network science is the detection of communities, which are sets of nodes in a network that are densely connected internally but sparsely connected to the rest of the network. A fundamental result in community detection is the existence of a nontrivial threshold for community detectability on sparse graphs that are generated by the planted partition model (PPM). Below this so-called “detectability limit”, no community-detection method can perform better than […]

Ver mais

A more comprehensive approach to probability studies an infinite number of probability laws that are formally admissible. Thus, an infinite number of weighted averages can be handled. Areinterpretation of the central limit theorem is accordingly shown. The deviations or errors from a fixed value are calculated. It is proved that they are normally distributed. Furthermore, such deviations are invariant with respect to geometric translations identifying repeated samples. In this paper, the way of understanding the statistical model to […]

Ver mais