This post describes my equipment and workflow for recording my digital piano and editing the recording for publishing online.

Experiment design and results for training RNN, GRU, and LSTM models on a dataset of single biological neuron inputs/outputs.

Exploratory data analysis, principal component analysis (PCA), and recurrent neural networks (RNNs) for neutrino reconstruction of an IceCube dataset for a Kaggle competition.

I share the data processing and loading steps, training workflow, and inference implementation used for a Kaggle competition on image classification of a mammography dataset.

Learn how to set up a multi-label audio tagging task as a computer vision classification problem. I’ll be covering my work and results in a past Kaggle competition (Freesound Audio Tagging 2019).

This blog post describes a machine learning tool to edit images through text-based prompts. It’s completely text-guided, so the user does not need to draw or provide a mask image of the areas to be edited.

I’ll demonstrate how to extract an audio clip from YouTube, implement speech recognition using OpenAI’s Whisper, and perform speech generation using Tortoise to clone a custom voice.

We’ll be deriving the equations to train a simple 2-layer neural network from scratch and implementing them in Python using the NumPy library.

I’m going to walk through my process implementing transfer learning in a computer vision classification problem using the PyTorch framework. I’ll briefly introduce the dataset used here, then cover the training and inference steps.

This tutorial introduces the PyTorch framework by applying it to a tabular dataset. The goal is to help you get PyTorch up and running using a simple dataset and model.

This beginner’s tutorial describes how to implement decision tree algorithms, namely random forests and gradient boosting machines. I’ll discuss how to train different models and search hyperparameters.

This post shows you how to set up a new website using Hugo (for building the site) and Cloudflare Pages (for hosting the site), based on my experience setting up this blog.