# Home

## Selected posts:

## ReAct REPL Agent

Project exploring a GPT-Based ReAct Agent with access to a Python REPL and access to method retrieval. The agent can execute simple workflows by chaining API calls.

## Implement a simple ReAct Agent using OpenAI

Simple example of using OpenAI Function Calling in a ReAct Loop to answer multistep questions.

## Implementing Gaussian processes

Blog series exploring Gaussian processes. Starts with building up an understanding of Gaussian processes by implementing them from scratch in Python. Then goes to a practical example illustrating how to use a Gaussian process on a real-world problem using TensorFlow probability.

## Multi-armed bandit implementation

Learn the basics of Bayesian multi-armed bandit models while implementing a simple example in Python.

## How to implement a neural network and RNN

First, Learn the basics of neural networks and how to implement them from scratch in Python. The tutorial starts with explaining gradient descent on the most basic models and goes along to explain hidden layers with non-linearities, backpropagation, and momentum. The math is explained along the way together with Python code examples.

The second part implements a recurrent neural network (RNN) in Python with the help of NumPy. The tutorial explains the basics of backpropagation-through-time and discusses some of the difficulties of training recurrent networks.

## Regression quattro stagioni

Linear regression parameter estimation implemented in four different ways: simple linear regression, ordinary least squares (OLS), gradient descent, and markov chain monte carlo (MCMC).