Tootfinder

"There’s a lot of debate about whether self-diagnosis for autism, ADHD and similar disabilities is valid. Here’s my position: self-diagnosis is the only valid form of diagnosis." https://freedomnews.org.uk/2024/02/29/autism-and-anarchy-self-diagnosis/<…

Has no one ever read Hyperion?
Fun project "Last digital common ancestor"
Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe.
https://github.com/mertyildiran/ldca

GitHub - mertyildiran/ldca: Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe (EXPERIMENTAL)
Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe (EXPERIMENTAL) - mertyildiran/ldca

Sorry, Zoomers, it's not us, it's you.
https://www.theguardian.com/music/2024/mar/29/song-lyrics-getting-simpler-more-repetitive-angry-and-self-obsessed-study

Oh no, look what self-driving truck AI has done to truck drivers
(Self-driving cars/trucks are almost completely a scam and just part of the ongoing AI hype.)

Hey song lyrics - ME TOO! 🤬
https://infosec.space/@AdminKirsty/112178143598263892

A look at the autonomous truck industry's challenges, including a lack of federal regulation, as Aurora and Kodiak plan a major expansion in Texas this year (Trisha Thadani/Washington Post)
https://wapo.st/3xlJxje

Ready or not, self-driving semi-trucks are coming to America’s highways
As several self-driving truck companies gain momentum around the country, state and federal lawmakers are grappling with how to regulate the new technology.

Has no one ever read Hyperion?
Fun project "Last digital common ancestor"
Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe.
https://github.com/mertyildiran/ldca

GitHub - mertyildiran/ldca: Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe (EXPERIMENTAL)
Self-replicating, self-modifying Assembly program that can evolve into every possible computer program in the universe (EXPERIMENTAL) - mertyildiran/ldca

Self-supervised learning for classifying paranasal anomalies in the maxillary sinus
Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Lennart Maack, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer
https://arxiv.org/abs/2404.18599 https://arxiv.org/pdf/2404.18599
arXiv:2404.18599v1 Announce Type: new
Abstract: Purpose: Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS).
Methods: Our approach uses a 3D Convolutional Autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D Convolutional Neural Network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images.
Results: The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an Area Under the Precision-Recall Curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and Masked Autoencoding using SparK at 0.75.
Conclusion: A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly

Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
https://arxiv.org/abs/2404.17140

Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether smaller-size (<= 13B) language models (LMs) have the ability of self-correction on reasoning tasks with minimal inputs from stronger LMs. We propose a novel pipeline that prompts smaller LMs to collect self-correction data that supports the training of self-ref…