iTransformer: The Latest Breakthrough in Time Series Forecasting

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…

The Math Behind LSTM

Dive into LSTMs, understand their mathematics, implement them from scratch, and explore their applications in algorithmic trading.

Bayesian Sensor Calibration

Glossary. The bolded terms are defined in the International Vocabulary of Metrology (known as the “VIM definitions”). Only the first occurrence is in bold. Code availability. An executable Jupyter…

This AI newsletter is all you need #94

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…

medium.com_towards-ai 3 weeks ago

Breaking down State-of-the-Art PPO Implementations in JAX

Since its publication in a 2017 paper by OpenAI, Proximal Policy Optimization (PPO) is widely regarded as one of the state-of-the-art algorithms in Reinforcement Learning. Indeed, PPO has…

Discover The Top 10 Most Used OpenAI GPTs

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…

medium.com_towards-ai 3 weeks ago

5 Ways to Serve Open Source LLMs (With Code Examples)

In the ever-evolving realm of Large Language Models (LLMs), the tools and techniques for serving them are advancing at a pace as swift as the models themselves. Unlike conventional models like…

Four Simple Steps to Build a Custom Self-Hosted Llama3 Application

Discover how to create a custom self-hosted Llama 3 chat assistant using Huggingface, Tornado, and Ngrok in four simple steps.

Tool Use, Agents, and the Voyager Paper

As LLMs continue to increase their reasoning ability, their capacity to plan and then act tends to increase. This has led to prompting templates where users give LLMs an end result they want and the…

3 Best Methods for Spatial Interpolation

Interpolation is a quite common mathematical concept, which is used not only by data scientists, but also people from a vast range of fields. However, when dealing with geospatial data, interpolation…