gkjohns

Re:BabyDS – An LLM driven data science AI on Monday April 17, 2023 @04:44PM (#35606374)

Here's a side project I've been working on. It allows the user to provide a dataset and an objective (Identify trends in country growth), analyzes the data, and returns a full report.

Please reach out to contribute! linkedin.com/in/gkjohns

BabyDS – An LLM driven data science AI

Posted by gkjohns on Monday April 17, 2023 @04:44PM
from the github.com dept.

https://github.com/Rock-River-Research/babyds

( Read More... | 1 comment | on HN )

Re:Simple example of machine learning in TensorFlow on Monday March 13, 2017 @03:41PM (#13861589)

a) it ensures that they're positive so they don't just cancel each other out and b) like you mentioned, it penalizes huge errors more heavily.

There are also historical reasons for using squared error. The square function is smooth and differentiable to you can analytically solve for the gradient. Before fast computers this was crucial for solving regression problems as a closed for makes everything easier.