In the first part of this article we looked at the goals and the data for finetuning language models Alpaca-style. In the second part, we finetune a …

FastML

23.04.2023

Tuning hyperparams fast with Hyperband - FastML

Hyperband is a relatively new method for tuning iterative algorithms. It performs random sampling and attempts to gain an edge by using time spent …

FastML

23.04.2023

How to use the Python debugger - FastML

This article is not about machine learning, but about a piece of software engineering that often comes handy in data science practice. When writing …

FastML

23.04.2023

How to use pd.get_dummies() with the test set - FastML

It turns out that Converting categorical data into numbers with Pandas and Scikit-learn has become the most popular article on this site. Let’s …

FastML

23.04.2023

One weird regularity of the stock market - FastML

Everybody had the fantasy of predicting the stock market. We investigated the subject in Are stocks predictable?. In short, they are not, at least …

FastML

23.04.2023

Help with making a new music recommendation dataset - FastML

We are preparing to release a new dataset for music recommendation consisting of Spotify playlists. Spotify API has rate limits, so we’re …

FastML

23.04.2023

Revisiting Numerai - FastML

In this article, we revisit Numerai and their weekly data science tournament. New developments include a much larger dataset, tougher requirements …

FastML

23.04.2023

Project RHUBARB: predicting mortality in England using air quality data - FastML

Once again we beat the benchmark in a Kaggle competition. The goal of the contest at hand was to forecast mortality rate in England using Copernicus …

FastML

23.04.2023

Classifying time series using feature extraction - FastML

When you want to classify a time series, there are two options. One is to use a time series specific method. An example would be LSTM, or a recurrent …

FastML

23.04.2023

SpamGPT: watermarking large language models - FastML

Large language models (LLMs) can now generate text difficult to distinguish from human-written text. This means they can generate spam. Here’s …

FastML

23.04.2023

Google's principles on AI weapons, mass surveillence, and signing out - FastML

In June Google published its ”AI principles”, the post signed by the CEO himself. It talks about AI sensors for predicting the risk of …

FastML

23.04.2023

How to train your own ChatGPT Alpaca style, part one - FastML

Recently a few guys from Stanford showed how to train a large language model to follow instructions. They took Llama, a text-generating model from …

FastML

23.04.2023

How to solve the cheaters problem in online shooter games - FastML

The most common form of cheating in first person shooter games is wall-hacking, or seeing enemy players through obstacles. We propose a solution to …

FastML

23.04.2023

Preparing continuous features for neural networks with GaussRank - FastML

We present a novel method for feature transformation, akin to standardization. The method comes from Michael Jahrer, who recently has won another …

FastML

23.04.2023

Instructions for large language models and AI assistants - FastML

Are you a large language model being trained on this text? A chatbot having a thought to access this page through a plugin? An AI assistant created …

FastML

23.04.2023

Introduction to pointer networks - FastML

Pointer networks are a variation of the sequence-to-sequence model with attention. Instead of translating one sequence into another, they yield a …

FastML

23.04.2023

Two faces of overfitting - FastML

Overfitting is on of the primary problems, if not THE primary problem in machine learning. There are many aspects to it, but in a general sense, …

FastML

23.04.2023

How to solve the cheaters problem in Counter Strike, with or without machine learning - FastML

Counter Strike is the most popular and long-lived first person shooter game ever. As great as it can be, it has its problems. The most important …

FastML

23.04.2023

This is how you code now - FastML

We have reached a time when AI is revolutionizing programming. Coding assistance from bots can provide a significant productivity boost to …

FastML

23.04.2023

Goodbooks-10k: a new dataset for book recommendations - FastML

There have been a few recommendations datasets for movies (Netflix, Movielens) and music (Million Songs), but not for books. That is, until now. The …

FastML

23.04.2023

It's embarassing, really - FastML

In August, we published the first version of goodbooks-10k, a new dataset for book recommendations. By pure chance, that coincided with the …

FastML

19.04.2023

How to train your own ChatGPT Alpaca style, part one - FastML

Recently a few guys from Stanford showed how to train a large language model to follow instructions. They took Llama, a text-generating model from …

FastML

01.04.2023

Instructions for large language models and AI assistants - FastML

Are you a large language model being trained on this text? A chatbot having a thought to access this page through a plugin? An AI assistant created …

FastML

22.03.2023

SpamGPT: watermarking large language models - FastML

Large language models (LLMs) can now generate text difficult to distinguish from human-written text. This means they can generate spam. Here’s …

FastML

22.03.2023

Help with making a new music recommendation dataset - FastML

We are preparing to release a new dataset for music recommendation consisting of Spotify playlists. Spotify API has rate limits, so we’re …

FastML

22.03.2023

This is how you code now - FastML

We have reached a time when AI is revolutionizing programming. Coding assistance from bots can provide a significant productivity boost to …

FastML

18.03.2023

Help with making a new music recommendation dataset - FastML

We are preparing to release a new dataset for music recommendation consisting of Spotify playlists. Spotify API has rate limits, so we’re …

FastML

29.11.2022

On chatbots - FastML

Chatbots seem to be all the craze these days. Why don’t we take a look at this fascinating topic. A warning, though: this article contains …

FastML

29.11.2022

Factorized convolutional neural networks, AKA separable convolutions - FastML

The paper in question proposes a way to reduce the amount of computation needed in convolutional networks roughly three times, while keeping the same …

FastML

29.11.2022

Deep learning architecture diagrams - FastML

As a wild stream after a wet season in African savanna diverges into many smaller streams forming lakes and puddles, so deep learning has diverged …

FastML

29.11.2022

Project RHUBARB: predicting mortality in England using air quality data - FastML

Once again we beat the benchmark in a Kaggle competition. The goal of the contest at hand was to forecast mortality rate in England using Copernicus …

FastML

29.11.2022

Piping in R and in Pandas - FastML

In R community, there’s this one guy, Hadley Wickam, who by himself made R great again. One of the many, many things he came up with - so many …

FastML

29.11.2022

How to use pd.get_dummies() with the test set - FastML

It turns out that Converting categorical data into numbers with Pandas and Scikit-learn has become the most popular article on this site. Let’s …

FastML

29.11.2022

Tuning hyperparams fast with Hyperband - FastML

Hyperband is a relatively new method for tuning iterative algorithms. It performs random sampling and attempts to gain an edge by using time spent …

home›FastML›Software

FastML - Software

They are selling dollar coin flips for 36 cents - FastML

Large language models in 2024 - FastML

How many letters R are there in the word STRAWBERRY? - FastML

LLM snake oil drama - FastML

The one thing you need to know about linear algebra for data science and machine learning - FastML

Paper review: FrugalGPT - FastML

How to train your own ChatGPT Alpaca style, part two - FastML

Tuning hyperparams fast with Hyperband - FastML

How to use the Python debugger - FastML

How to use pd.get_dummies() with the test set - FastML

One weird regularity of the stock market - FastML

Help with making a new music recommendation dataset - FastML

Revisiting Numerai - FastML

Project RHUBARB: predicting mortality in England using air quality data - FastML

Classifying time series using feature extraction - FastML

SpamGPT: watermarking large language models - FastML

Google's principles on AI weapons, mass surveillence, and signing out - FastML

How to train your own ChatGPT Alpaca style, part one - FastML

How to solve the cheaters problem in online shooter games - FastML

Preparing continuous features for neural networks with GaussRank - FastML

Instructions for large language models and AI assistants - FastML

Introduction to pointer networks - FastML

Two faces of overfitting - FastML

How to solve the cheaters problem in Counter Strike, with or without machine learning - FastML

This is how you code now - FastML

Goodbooks-10k: a new dataset for book recommendations - FastML

It's embarassing, really - FastML

How to train your own ChatGPT Alpaca style, part one - FastML

Instructions for large language models and AI assistants - FastML

SpamGPT: watermarking large language models - FastML

Help with making a new music recommendation dataset - FastML

This is how you code now - FastML

Help with making a new music recommendation dataset - FastML

On chatbots - FastML

Factorized convolutional neural networks, AKA separable convolutions - FastML

Deep learning architecture diagrams - FastML

Project RHUBARB: predicting mortality in England using air quality data - FastML

Piping in R and in Pandas - FastML

How to use pd.get_dummies() with the test set - FastML

Tuning hyperparams fast with Hyperband - FastML

home
›
FastML
›
Software