I wanted to share my work from an LLM hackathon hosted by Deonna and Nick from AVL Digital Nomads. I recently have been reading “The Art of Gathering” by Priya Parker, which I recommend (see also: her TED talk and podcast). The goal was to create an assistant to help...
[Read More]
Getting Immersed VR setup on Ubuntu
Documenting how to get Immersed VR working on Ubuntu Linux
In my quest to perfect my “road warrior” setup, I have been experimenting with coding in VR. I have been using the Immersed VR app on my Quest 3 headset to create a virtual workspace. Unfortunately, the official Immersed documentation is not very clear on how to get Immersed VR...
[Read More]
Richard's ML Study Guide
A collection of study materials for machine learning.
I’ve been asked a few times for recommendations on how to get started studying machine learning. I am sharing it here for anyone who is interested, and I will update it as I find new resources.
This guide is meant for people with little to no experience.
[Read More]
How to do stratified splitting of Multi-class Multi-labeled image classification data
Complete with code and unit tests.
Stratified sampling is imporant when you have extremely unbalanced machine learning datasets to ensure that each class is evenly distributed across your train/test/validation splits. While there are several solutions for multi-class data, there are few for multi-classs and multi-label datasets. So, I’m sharing my solution below.
[Read More]
Automatically creating Kedro dataset directories
Avoiding IO errors at the end of pipelines with a simple hook.
If you use Kedro for data pipelines, you may have had issues saving datasets if the dataset directory does not already exist. Instead of manually creating these data folders, here is a hook which automatically creates any missing directories. In the process, it’ll also automatically generate a .gitkeep file.
[Read More]
-
LLM Assistant for Better Gatherings
Using a daisy chain of prompts to plan a potluck
I wanted to share my work from an LLM hackathon hosted by Deonna and Nick from AVL Digital Nomads. I recently have been reading “The Art of Gathering” by Priya Parker, which I recommend (see also: her TED talk and podcast). The goal was to create an assistant to help... [Read More] -
Getting Immersed VR setup on Ubuntu
Documenting how to get Immersed VR working on Ubuntu Linux
In my quest to perfect my “road warrior” setup, I have been experimenting with coding in VR. I have been using the Immersed VR app on my Quest 3 headset to create a virtual workspace. Unfortunately, the official Immersed documentation is not very clear on how to get Immersed VR... [Read More] -
Richard's ML Study Guide
A collection of study materials for machine learning.
I’ve been asked a few times for recommendations on how to get started studying machine learning. I am sharing it here for anyone who is interested, and I will update it as I find new resources. This guide is meant for people with little to no experience. [Read More] -
How to do stratified splitting of Multi-class Multi-labeled image classification data
Complete with code and unit tests.
Stratified sampling is imporant when you have extremely unbalanced machine learning datasets to ensure that each class is evenly distributed across your train/test/validation splits. While there are several solutions for multi-class data, there are few for multi-classs and multi-label datasets. So, I’m sharing my solution below. [Read More] -
Automatically creating Kedro dataset directories
Avoiding IO errors at the end of pipelines with a simple hook.
If you use Kedro for data pipelines, you may have had issues saving datasets if the dataset directory does not already exist. Instead of manually creating these data folders, here is a hook which automatically creates any missing directories. In the process, it’ll also automatically generate a .gitkeep file. [Read More]