Please turn JavaScript on
Homepage
TrendingMy newsFind FeedsDelivery settingsPlansMy earnings
HelpBlog
Log in
Find more feeds
header-image

Master Data Science

We bring you the latest updates from Master Data Science through a simple and fast subscription.

We can deliver your news in your inbox, on your phone or you can read them here on this website on your personal news page.

Unsubscribe at any time without hassle.

Master Data Science's title: Master Data Science - Master Data Science

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.33 / day

Message History

dH #011: Diffusion Models — From Noise to Wolves, Training from Scratch

In this post we build a complete diffusion model from scratch — training a UNet on a custom dataset, implementing the full DDPM pipeline, and understanding the math that makes iterative denoising work. We cover noise schedules, the reparameterization trick, FID evaluation, and three diffusion objectives (ε, x₀, v). By the end you’ll have generated novel images from pure Gauss...


Read full story
LLM_log #010 Understanding Diffusion Models Through 1D Experiments — From DDPM to Manifold Compactness

Highlights: We implement a complete DDPM from scratch on 1D sine waves — same math as image diffusion, but every intermediate state is plottable. We track 100 parallel trajectories, measure when the model “commits” to a specific sample, then design a controlled experiment that reveals manifold compactness as the key factor determining whether diffusion succeeds or fails. So l...


Read full story
dH #009: An Image is Worth 16×16 Words — From Transformers to Vision Transformers and SWIN

Highlights: In this post, we take a deep dive into the architecture that changed everything — the Transformer — and trace its evolution from NLP into computer vision. We start with the original encoder-decoder model, walk through self-attention and multi-head attention step by step, and then show how Vision Transformers (ViT) apply the exact same mechanism to image patches in...


Read full story
LLM_log #008: CLIP — Understanding Multimodal AI Through Step-by-Step Experiments

  Highlights: In this post, you’ll learn how CLIP connects images and text in a shared embedding space — enabling zero-shot image classification, semantic search, and visual perception scoring without any task-specific training. We start from the ground up with Vision Transformers, walk through CLIP’s contrastive learning architecture, run hands-on embedding experiments,...


Read full story
LLM_log #007: From Random Text to Coherent Language – Pretraining Your First Large Language Model

Highlights: In this guide, you’ll learn how to pretrain a large language model from scratch — implementing training loops, evaluation metrics, and advanced text generation strategies. We’ll build a complete GPT-style training pipeline, watch it evolve from random gibberish to coherent text, and explore techniques like temperature scaling and top-k sampling. By the end, you’ll...


Read full story