Related papers: Primate specific retrotransposons, SVAs, in the ev…
In this study, the partially entangled neural networks is used to transfer information between two neurons, where the original teleportation protocol is employed this for this purpose. The effect of the network strength on the fidelity of…
Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. This is not…
Symbolic reasoning and neural networks are often considered incompatible approaches. Connectionist models known as Vector Symbolic Architectures (VSAs) can potentially bridge this gap. However, classical VSAs and neural networks are still…
Signal transduction pathways are largely conserved throughout the animal kingdom. The repertoire of pathways is limited and each pathway is used in different intercellular signaling events during the development of a given animal. For…
Humans see low spatial frequency components before high spatial frequency components. Drawing on this neuroscientific inspiration, we investigate the effect of introducing patches from different spatial frequencies into Vision Transformers…
Fetal neuroinflammation and prenatal stress (PS) may contribute to lifelong neurological disabilities. Astrocytes and microglia, among the brain's non-neuronal glia cell populations, play a pivotal role in neurodevelopment, predisposition…
A number of studies have indicated a potential association between prenatal exposure to radiation and late mental disabilities. This is believed to be due to long-term developmental changes and functional impairment of the central nervous…
What types of numeric representations emerge in neural systems, and what would a satisfying answer to this question look like? In this work, we interpret Neural Network (NN) solutions to sequence based number tasks using a variety of…
Background: Non-linear alterations in brain network connectivity may represent early neural signatures of Alzheimer's disease (AD) pathology in cognitively normal older adults. Understanding these changes and their cognitive relevance may…
Sparse Attention Vectors (SAVs) have emerged as an excellent training-free alternative to supervised finetuning or low-rank adaptation to improve the performance of Vision Language Models (VLMs). At their heart, SAVs select a few accurate…
Recent advances in embodied intelligence have leveraged massive scaling of data and model parameters to master natural-language command following and multi-task control. In contrast, biological systems demonstrate an innate ability to…
In studying primate vision, a large body of work focuses on the first feedforward sweep. During this initial time window, information is thought to pass through ventral stream regions in a stage-like fashion in an effort to extract…
Neurons can display highly variable dynamics. While such variability presumably supports the wide range of behaviors generated by the organism, their gene expressions are relatively stable in the adult brain. This suggests that neuronal…
The human brains are organized into hierarchically modular networks facilitating efficient and stable information processing and supporting diverse cognitive processes during the course of development. While the remarkable reconfiguration…
Despite significant progress in structural and functional characterization of human genome, understanding of mechanisms underlying the genetic basis of human phenotypic uniqueness remains limited. We report that non-randomly distributed…
Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence…
Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…
Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become essential to foundation models, allowing excellent performance on diverse downstream tasks with minimal adaptation. Consequently, there is growing…
Spiking neural networks (SNNs) that enable low-power design on edge devices have recently attracted significant research. However, the temporal characteristic of SNNs causes high latency, high bandwidth and high energy consumption for the…
Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Transformers face two…