magnASCII.dev Simone Magnaschi
Senior Full Stack Web Dev
Bookmarks tagged with #machine-learning.
Show all

I Built an LLM From Scratch

In this video CJ explains chat bots, neural networks, tokenization, embeddings, transformers and more. He shows real working code for everything and gives hi...
Saved on: 2026-07-21

How LLMs Actually Work

A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
Saved on: 2026-06-06

From Kevin Bacon to HNSW: the intuition behind semantic search and vector databases

An explainer to how modern fast and accurate vector searching works, with interactive demos.
Saved on: 2025-11-12

A visual exploration of vector embeddings

For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size . In this post, I'll translate ...
Saved on: 2025-05-30

Deep Dive into LLMs like ChatGPT

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full traini...
Saved on: 2025-02-06

(44) Vectors in SQLite! (with libSQL) - YouTube

In this video, I explore how to improve related article recommendations on a website by leveraging SQLite with experimental vector support in libSQL, a packa...
Saved on: 2024-10-27

The Super Effectiveness of Pokémon Embeddings Using Only Raw JSON and Image

Embeddings encourage engineers to go full YOLO because it’s actually rewarding to do so!
Saved on: 2024-07-01

Distill — Latest articles about machine learning

Articles about Machine Learning
Saved on: 2023-12-20

Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

Stable Audio represents the cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllability, inference speed, and output length.
Saved on: 2023-09-13

Using GPT-4 to measure the passage of time in fiction – The Stone and the S

Large language models are valuable research assistants, especially when they refuse to follow instructions.
Saved on: 2023-06-23

Online gradient descent written in SQL • Max Halford

Edit – this post generated a few insightful comments on Hacker News. I’ve also put the code in a notebook for ease of use. Introduction Modern MLOps is complex because it involves too many components. You need a message bus, a stream processing engine, an API, a model store, a feature store, a monitoring service, etc. Sadly, containerisation software and the unbundling trend have encouraged an appetite for complexity. I believe MLOps shouldn’t be this complex. For instance, MLOps can be made simpler by bundling the logic into your database.
Saved on: 2023-03-08

What Is ChatGPT Doing … and Why Does It Work?—Stephen Wolfram Writings

Stephen Wolfram explores the broader picture of what's going on inside ChatGPT and why it produces meaningful text. Discusses models, training neural nets, embeddings, tokens, transformers, language syntax.
Saved on: 2023-02-15

GPT in 60 Lines of NumPy | Jay Mody

Implementing a GPT model from scratch in NumPy.
Saved on: 2023-02-10

The Dynamics of Exploration on Spotify | Spotify Research

“Variety is the spice of life”, as the saying attributed to poet William Cowper goes. People crave heterogeneity and avoid boredom across all aspects of their online experiences. As services that provide vast amounts of content for user consumption, streaming platforms like Spotify are keen to better understand how people seek out variety to keep themselves interested and engaged. If we can figure out when and how listeners want to expand their musical tastes, then mechanisms like recommender systems could help them find novel pieces of music.
Saved on: 2022-07-30

GPT3 Empowered Recommendation System | by Cheng He | The Startup | Sep, 202

Recommendation systems are so successful in many products and services we interact with every day. Like 40% of app installs on Google Play and 60% of watch time on YouTube comes from recommendations…
Saved on: 2020-09-09

RubixML/RubixML: Rubix ML is a high-level machine learning library that let

A high-level machine learning and deep learning library for the PHP language. - RubixML/ML
Saved on: 2018-12-21

Making 1M Click Predictions per Second using AWS - AdRoll

Click prediction may be a simple binary classification problem, but it requires a robust system architecture to function in production at scale. At AdRoll, we leverage the AWS ecosystem along with a suite of third party tools to build the predictors that power our pricing engine, BidIQ. This is a tour of the production pipelines and monitoring systems that keep BidIQ running.
Saved on: 2018-04-27

Jason's Machine Learning 101 - Presentazioni Google

Jason Mayes Senior Creative Engineer, Google Machine Learning 101 Feel free to share this deck with others who are learning! Send me feedback here. Dec 2017 Welcome! If you are reading the notes there are a few extra snippets down here from time to time. But more for my own thoughts, feel free to...
Saved on: 2017-12-14

Machine Learning for Humans🤖👶 - Machine Learning for Humans - Medium

The ultimate guide to machine learning. Simple, plain-English explanations accompanied by math, code, and real-world examples.
Saved on: 2017-08-19

Announcing AudioSet: A Dataset for Audio Event Research

Posted by Dan Ellis, Research Scientist, Sound Understanding TeamSystems able to recognize sounds familiar to human listeners have a wide range of ...
Saved on: 2017-04-03

Welcome to the New AWS AI Blog! | AWS AI Blog

If you ask 100 people for the definition of “artificial intelligence,” you’ll get at least 100 answers, if not more. At AWS, we define it as a service or system which can perform tasks that usually require human-level intelligence such as visual perception, speech recognition, decision making, or translation. On this new AWS blog, we’ll […]
Saved on: 2017-02-21

Learning Machine Learning: A beginner's journey

I have been learning about machine learning and deep learning (ML/DL) for the last year. I think ML/DL is here to stay. I don't think th...
Saved on: 2016-12-26

DeepRhyme (D-Prime) – generating dope rhymes with deep learning | Mike Swar

Disclaimer : I am a white boy, straight outta Cambridge, UK.  I do not condone the nastier, sometimes misogynistic language in this post, but in the interest of keeping it real, I have not made any…
Saved on: 2016-11-07

Grokking Deep Learning - i am trask

A machine learning craftsmanship blog.
Saved on: 2016-08-18

Mapping the World of Music Using Machine Learning: Part 1 — iHeartRadio Tec

In June 2016 Ravi Mody and Tim Schmeier gave a presentation at the NYC Machine Learning meetup to discuss their work on the data science team at iHeartRadio. This is the first in a three part article…
Saved on: 2016-08-11

A Simple Content-Based Recommendation Engine in Python - blog.untrod.com

Let's pretend we need to build a recommendation engine for an eCommerce web site. There are basically two approaches you can take: content-based and collaborative-filtering. We'll look at some...
Saved on: 2016-06-12

Boosting Sales With Machine Learning — Xeneta — Medium

In this blog post I’ll explain how we’re making our sales process at Xeneta more effective by training a machine learning algorithm to predict the quality of our leads based upon their company…
Saved on: 2016-06-08

tflearn/README.md at 0.1.0 · tflearn/tflearn

Deep learning library featuring a higher-level API for TensorFlow. - tflearn/tflearn
Saved on: 2016-04-21

Learn the Latest Tech Skills; Advance Your Career | Udacity

Learn online and advance your career with courses in programming, data science, artificial intelligence, digital marketing, and more. Gain in-demand technical skills. Join today!
Saved on: 2016-01-22

Google Cloud Vision API changes the way applications understand images

Have you ever wondered how Google Photos helps you find all your favorite dog photos? With today’s release of Google Cloud Vision API , deve...
Saved on: 2015-12-02

QA Platform

Accelerate progress up the cloud curve with Cloud Academy's digital training solutions. Build a culture of cloud with technology and guided learning experiences.
Saved on: 2015-04-29

Text Analysis blog | Aylien — Text Analysis and PHP: Getting Started with A

Check out our blog for risk analyst news such as risk intelligence trends or risk management frameworks. Here you can find all about news monitoring.
Saved on: 2014-12-12

ArmenAg/Improvisation: A program that learns music structure of given midi files and able to generate new melodies by judmental of other compositions. E.g. generate melody in style of Armstrong as negatively judged by Eminem and...

A program that learns music structure of given midi files and able to generate new melodies by judmental of other compositions. E.g. generate melody in style of Armstrong as negatively judged by Em...
Saved on: 2014-10-10
❤️
</>
2026