Fashion

Today’s model is Logistic Regression. If you already know this model, here is a question for you: Is Logistic Regression a regressor or a classifier? Well, this question is exactly like: Is a tomato a fruit or a vegetable? From a botanist’s viewpoint, a tomato is a fruit, because they look at structure: seeds, flowers, plant biology. From a cook’s …

Regression, finally! For Day 11, I waited many days to present this model. It marks the beginning of a new journey in this “Advent Calendar“. Until now, we mostly looked at models based on distances, neighbors, or local density. As you may know, for tabular data, decision trees, especially ensembles of decision trees, are very performant. But starting today, we …

[Submitted on 11 Apr 2025 (v1), last revised 9 Dec 2025 (this version, v4)] View a PDF of the paper titled Rethinking Few-Shot Image Fusion: Granular Ball Priors Enable General-Purpose Deep Fusion, by Minjie Deng and 5 other authors View PDF HTML (experimental) Abstract:In image fusion tasks, the absence of real fused images as priors forces most deep learning approaches …

arXiv:2512.07224v1 Announce Type: cross Abstract: Segmentation is the identification of anatomical regions of interest, such as organs, tissue, and lesions, serving as a fundamental task in computer-aided diagnosis in medical imaging. Although deep learning models have achieved remarkable performance in medical image segmentation, the need for explainability remains critical for ensuring their acceptance and integration in clinical practice, despite the …

with Decision Trees, both for Regression and Classification, we will continue to use the principle of Decision Trees today. And this time, we are in unsupervised learning, so there are no labels. The algorithm is called Isolation Forest, and the idea is to build many decision trees to form a forest. The principle is to detect anomalies by isolating them. …

While OpenAI continues to insist that there are currently no ads — or tests for advertising — live in ChatGPT, the company’s chief research officer Mark Chen also acknowledged that the company “fell short” with recent promotional messages and is working to improve the experience. Chen and other OpenAI executives were responding to posts from ChatGPT’s paying subscribers who complained …

an interesting conversation on X about how it is becoming difficult to keep up with new research papers because of their ever-increasing quantity. Honestly, it’s a general consensus that it’s impossible to keep up with all the research that is currently happening in the AI space, and if we are not able to keep up, we are then missing out …

Three years ago, ChatGPT was born. It amazed the world and ignited unprecedented investment and excitement in AI. Today, ChatGPT is still a toddler, but public sentiment around the AI boom has turned sharply negative. The shift began when OpenAI released GPT-5 this summer to mixed reviews, mostly from casual users who, unsurprisingly, judged the system by its surface flaws …

paper from Konrad Körding’s Lab [1], “Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?” gives insights into a foundational question in visual neuroscience: what is required to bind visual elements and textures together as objects? The goal of this article is to give you a background on this problem, review this NeurIPS paper, and hopefully give you insight …

[Submitted on 30 Jan 2025 (v1), last revised 1 Dec 2025 (this version, v2)] View a PDF of the paper titled Decentralized Projection-free Online Upper-Linearizable Optimization with Applications to DR-Submodular Optimization, by Yiyang Lu and 2 other authors View PDF HTML (experimental) Abstract:We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-linearizable …