Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mamot.fr is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mamot.fr est un serveur Mastodon francophone, géré par La Quadrature du Net.

Administered by:

Server stats:

3.5K
active users

mamot.fr: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.4

#compsci

48 posts30 participants6 posts today
Public *
Cable Green, PhD

Outdated computer science textbooks? No thanks! Since the resources in OpenStax's new computer science digital collection are @creativecommons licensed open educational resources, they are designed to actively evolve with the industry. news.rice.edu/news/2025/openst #OER #CompSci

Rice News | News and Media Relations | Rice UniversityOpenStax announces completed computer science collectionOpenStax, a leading provider of high-quality open educational resources and interactive learning technologies housed at Rice, announces the completion of its computer science digital textbook collection. These resources provide free, up-to-date, relevant and engaging learning content to support students and educators in one of today’s most popular and rapidly evolving fields.
Public
Compsci Weekly

[R] Position: Model Collapse Does Not Mean What You Think

arxiv.org/abs/2503.03150

Discussions: discu.eu/q/https://arxiv.org/a

arXiv logo
arXiv.orgPosition: Model Collapse Does Not Mean What You ThinkThe proliferation of AI-generated content online has fueled concerns over \emph{model collapse}, a degradation in future generative models' performance when trained on synthetic data generated by earlier models. Industry leaders, premier research journals and popular science publications alike have prophesied catastrophic societal consequences stemming from model collapse. In this position piece, we contend this widespread narrative fundamentally misunderstands the scientific evidence. We highlight that research on model collapse actually encompasses eight distinct and at times conflicting definitions of model collapse, and argue that inconsistent terminology within and between papers has hindered building a comprehensive understanding of model collapse. To assess how significantly different interpretations of model collapse threaten future generative models, we posit what we believe are realistic conditions for studying model collapse and then conduct a rigorous assessment of the literature's methodologies through this lens. While we leave room for reasonable disagreement, our analysis of research studies, weighted by how faithfully each study matches real-world conditions, leads us to conclude that certain predicted claims of model collapse rely on assumptions and conditions that poorly match real-world conditions, and in fact several prominent collapse scenarios are readily avoidable. Altogether, this position paper argues that model collapse has been warped from a nuanced multifaceted consideration into an oversimplified threat, and that the evidence suggests specific harms more likely under society's current trajectory have received disproportionately less attention.
#compsci#machinelearning
Public
Compsci Weekly

[R] NeuRaLaTeX: A machine learning library written in pure LaTeX

arxiv.org/abs/2503.24187

Discussions: discu.eu/q/https://arxiv.org/a

arXiv logo
arXiv.orgNeuRaLaTeX: A machine learning library written in pure LaTeXIn this paper, we introduce NeuRaLaTeX, which we believe to be the first deep learning library written entirely in LaTeX. As part of your LaTeX document you can specify the architecture of a neural network and its loss functions, define how to generate or load training data, and specify training hyperparameters and experiments. When the document is compiled, the LaTeX compiler will generate or load training data, train the network, run experiments, and generate figures. This paper generates a random 100 point spiral dataset, trains a two layer MLP on it, evaluates on a different random spiral dataset, produces plots and tables of results. The paper took 48 hours to compile and the entire source code for NeuRaLaTeX is contained within the source code of the paper. We propose two new metrics: the Written In Latex (WIL) metric measures the proportion of a machine learning library that is written in pure LaTeX, while the Source Code Of Method in Source Code of Paper (SCOMISCOP) metric measures the proportion of a paper's implementation that is contained within the paper source. We are state-of-the-art for both metrics, outperforming the ResNet and Transformer papers, as well as the PyTorch and Tensorflow libraries. Source code, documentation, videos, crypto scams and an invitation to invest in the commercialisation of NeuRaLaTeX are available at https://www.neuralatex.com
#compsci#machinelearning
ExploreLive feeds
About