Highest Rated Papers

Rating: Highest Clear all

Advanced filtersTopic: All

Experimental

Topic

Topics are auto-detected from title, abstract, and metadata and may be imperfect.

Publication Date

Newest Oldest

Average Rating

Highest Lowest Clear

Female Rebellion Bound by Culture: A Comparative Study of Lin Daiyu and Anna Karenina’s Struggles Against Societal Expectations

Anqi Song

Arts, Culture and Language·2024

Lin Daiyu and Anna Karenina are female protagonists in Cao Xueqin’s Dream of the Red Chamber and Leo Tolstoy’s Anna Karenina, two masterpieces of world literature. Despite their geographical and cultural differences, both characters engage in acts of defiance against social norms that reflect their desires for autonomy, love, and self-expression. This paper explores the similarities and differences of their rebellions, including their driving force, detailed rebellious acts, the ending of their rebellions, and the cultural elements involved. By analyzing their gender roles under different cultural contexts, this paper seeks to uncover the universal social constraints carried upon women, and their different embodiment because of cultural and social structure demonstrated in the literature. The comparative study sheds light on the broader implications of female resistance in literature and how these narratives contribute to the discourse on gender and societal changes. This research applies gynocriticism in feminist criticism to provide a comprehensive understanding of women’s internal consciousness embodied in literature across cultures.

No ratings yet

View paper →

Disclosing Submillimeter Galaxy Formation: Mergers or Secular Evolution?

Siu-Wang 瀟弘 Chan 陳, Yiping Ao, Qing-hua Tan

The Astrophysical Journal·2025

We analyze the morphology of 125 submillimeter galaxies (SMGs) in the PRIMER-COSMOS field using double Sérsic modeling on JWST NIRCam images across six bands (F150W, F200W, F277W, F356W, F410M, and F444W), with SMGs being classified by the bulge Sérsic index (n_bulge) and bulge-to-total luminosity ratio (B/T). The Kolmogorov–Smirnov test between the bright (SFR > 175M⊙ yr−1) and the faint groups (SFR 0.5, n > 4) versus pseudo-bulges (B/T < 0.35, n < 2). In the F277W, nonparametric morphological measurements indicate predominantly disk-dominated patterns, with only 24% of SMGs demonstrating merger signatures. After the removal of SMGs with disturbed morphology, the bulge classification scheme in F277W shows pseudo-bulges (21%) and clump migration bulges (16%) from secular evolution, compared to 4% merger-built bulges. Surprisingly, 48% of SMGs defy the classification scheme, showing high B/T (∼0.7) but low Sérsic index (n_bulge ≤ 1). Bars are confirmed in 7% of SMGs. This work suggests that secular evolution takes precedence over major mergers, supporting the idea that isolated evolution fueled by filamentary gas inflow plays a nonnegligible role in the formation of SMGs.

No ratings yet

View paper →

(PDF) Essentialism and Anti-Essentialism in Feminist Philosophy

https://lancaster.academia.edu/AlisonStone

academia.edu·2012

This article revisits the ethical and political questions raised by feminist debates over essentialism, the belief that there are properties essential to women and which all women share. Feminists' widespread rejection of essentialism has

No ratings yet

View paper →

PreviousPage 193 of 475Next

On the Relationship between Self-Attention and Convolutional Layers

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi

arXiv·2019

Recent trends of incorporating attention mechanisms in vision have led researchers to reconsider the supremacy of convolutional layers as a primary building block. Beyond helping CNNs to handle long-range dependencies, Ramachandran et al. (2019) showed that attention can completely replace convolution and achieve state-of-the-art performance on vision tasks. This raises the question: do learned attention layers operate similarly to convolutional layers? This work provides evidence that attention layers can perform convolution and, indeed, they often learn to do so in practice. Specifically, we prove that a multi-head self-attention layer with sufficient number of heads is at least as expressive as any convolutional layer. Our numerical experiments then show that self-attention layers attend to pixel-grid patterns similarly to CNN layers, corroborating our analysis. Our code is publicly available.

No ratings yet

View paper →

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

Yihao Li

openreview.net

Object binding, the brain’s ability to bind the many features that collectively represent an object into a coherent whole, is central to human cognition. It groups low-level perceptual features into high-level object representations, stores those objects efficiently and compositionally in memory, and supports human reasoning about individual object instances. While prior work often imposes object-centric attention (e.g., Slot Attention) explicitly to probe these benefits, it remains unclear whether this ability naturally emerges in pre-trained Vision Transformers (ViTs). Intuitively, they could: recognizing which patches belong to the same object should be useful for downstream prediction and thus guide attention. Motivated by the quadratic nature of self-attention, we hypothesize that ViTs represent whether two patches belong to the same object, a property we term IsSameObject. We decode IsSameObject from patch embeddings across ViT layers using a similarity probe, which reaches over 90% accuracy. Crucially, this object-binding capability emerges reliably in self-supervised ViTs (DINO, MAE, CLIP), but markedly weaker in ImageNet-supervised models, suggesting that binding is not a trivial architectural artifact, but an ability acquired through specific pretraining objectives. We further discover that IsSameObject is encoded in a low-dimensional subspace on top of object features, and that this signal actively guides attention. AblatingIsSameObject from model activations degrades downstream performance and works against the learning objective, implying that emergent object binding naturally serves the pretraining objective. Our findings challenge the view that ViTs lack object binding and highlight how symbolic knowledge of “which parts belong together” emerges naturally in a connectionist system.

No ratings yet

View paper →

Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex

Rajesh P. N. Rao, Dana H. Ballard

Neural Computation·1997·194 citations

The responses of visual cortical neurons during fixation tasks can be significantly modulated by stimuli from beyond the classical receptive field. Modulatory effects in neural responses have also been recently reported in a task where a monkey freely views a natural scene. In this article, we describe a hierarchical network model of visual recognition that explains these experimental observations by using a form of the extended Kalman filter as given by the minimum description length (MDL) principle. The model dynamically combines input-driven bottom-up signals with expectation-driven top-down signals to predict current recognition state. Synaptic weights in the model are adapted in a Hebbian manner according to a learning rule also derived from the MDL principle. The resulting prediction-learning scheme can be viewed as implementing a form of the expectation-maximization (EM) algorithm. The architecture of the model posits an active computational role for the reciprocal connections between adjoining visual cortical areas in determining neural response properties. In particular, the model demonstrates the possible role of feedback from higher cortical areas in mediating neurophysiological effects due to stimuli from beyond the classical receptive field. Simulations of the model are provided that help explain the experimental observations regarding neural responses in both free viewing and fixating conditions.

No ratings yet

View paper →

Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future

Grace W. Lindsay

Journal of Cognitive Neuroscience·2021·377 citations

Convolutional neural networks (CNNs) were inspired by early findings in the study of biological vision. They have since become successful tools in computer vision and state-of-the-art models of both neural activity and behavior on visual tasks. This review highlights what, in the context of CNNs, it means to be a good model in computational neuroscience and the various ways models can provide insight. Specifically, it covers the origins of CNNs and the methods by which we validate them as models of biological vision. It then goes on to elaborate on what we can learn about biological vision by understanding and experimenting on CNNs and discusses emerging opportunities for the use of CNNs in vision research beyond basic object recognition.

No ratings yet

View paper →

Transformations of Lamarckism: From Subtle Fluids to Molecular Biology - Google Books

Unknown Author

Google Books

In 1809 -- the year of Charles Darwin's birth -- Jean-Baptiste Lamarck published Philosophie zoologique, the first comprehensive and systematic theory of biological evolution. The Lamarckian approach emphasizes the generation of developmental variations; Darwinism stresses selection. Lamarck's ideas were eventually eclipsed by Darwinian concepts, especially after the emergence of the Modern Synthesis in the twentieth century. The different approaches -- which can be seen as complementary rather than mutually exclusive -- have important implications for the kinds of questions biologists ask and for the type of research they conduct. Lamarckism has been evolving -- or, in Lamarckian terminology, transforming -- since Philosophie zoologique's description of biological processes mediated by "subtle fluids." Essays in this book focus on new developments in biology that make Lamarck's ideas relevant not only to modern empirical and theoretical research but also to problems in the philosophy of biology. Contributors discuss the historical transformations of Lamarckism from the 1820s to the 1940s, and the different understandings of Lamarck and Lamarckism; the Modern Synthesis and its emphasis on Mendelian genetics; theoretical and experimental research on such "Lamarckian" topics as plasticity, soft (epigenetic) inheritance, and individuality; and the importance of a developmental approach to evolution in the philosophy of biology. The book shows the advantages of a "Lamarckian" perspective on evolution. Indeed, the development-oriented approach it presents is becoming central to current evolutionary studies -- as can be seen in the burgeoning field of Evo-Devo. Transformations of Lamarckism makes a unique contribution to this research.

No ratings yet

View paper →

Highest Rated Papers

Female Rebellion Bound by Culture: A Comparative Study of Lin Daiyu and Anna Karenina’s Struggles Against Societal Expectations

Disclosing Submillimeter Galaxy Formation: Mergers or Secular Evolution?

(PDF) Essentialism and Anti-Essentialism in Feminist Philosophy

Are ViTs As Global As We Think

On the Relationship between Self-Attention and Convolutional Layers

Do Vision Transformers See Like Convolutional Neural Networks?

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex

Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future

Sergey Tsokolov: A Brief Life In Science

Transformations of Lamarckism: From Subtle Fluids to Molecular Biology - Google Books

Listening Otherwise, Music Miniaturized: A Different Type of Question about Revolution