There was a time when I worked in data for a seed venture capital firm. Part of my job in the VC fund was to discuss with entrepreneurs the indicators of Product-Market Fit in their business. I used…
A new unsupervised method that combines two concepts of vector quantization and space-filling curves to interpret the latent space of DNNs.
Have you ever had a need for a dataset that doesn’t easily exist? Wanted to easily generate data that matches your exact requirements for interviewing prospective data science candidates, software…
When dealing with discrete random variables, the joint probability mass function (PMF) is a fundamental concept in probability theory and statistics. Understanding it is crucial for analyzing the…
Prompt engineering for interactive Python Streamlit maps. “Simple Streamlit Sliders: Intaractive Map Visuals with GPT-4 Prompting” is published by John Loewen, PhD in Towards AI.
In this tutorial, we will explore promptrefiner: A tiny python tool I have created to create perfect system prompts for your local LLM, by using the help of the GPT-4 model. Crafting an effective and…
Reinforcement learning is a special domain in machine learning that differs a lot from the classic methods used in supervised or unsupervised learning. The beauty of reinforcement learning is that…
The field of forecasting has seen a lot of activity in the realm of foundation models, with models like Lag-LLaMA, Time-LLM, Chronos and Moirai being proposed since the beginning of 2024. However…
For the past few weeks, we have been following an increased pace of voice and music AI model releases. In particular, Suno AI’s v3 music generation model was released two weeks ago and has gained…
In November 2023, almost one year after ChatGPT 3 was released, OpenAI announced GPTs, allowing users to create and publish their own conversational chatbots, customized as per their instructions…