Daniel Furman's Projects
A collaborative book on algorithms
An audio deep learning mini-lesson from the 2021 DAT/Artathon fellowship.
Text clustering: HDBSCAN is probably all you need.
Code for STFT Transformer used in BirdCLEF 2021 competition.
The blockCV package creates spatially or environmentally separated training and testing folds for cross-validation to provide a robust error estimation in spatially structured environments. See
Data for the Sartorius Cell Instance Segmentation comp with cellpose transforms.
RAG chatbot built on top of trending M&A news.
Lightweight demo of gpt-3.5-turbo conversation completion.
A collection of MATLAB scripts from undergraduate math classes. Focus on numerical methods and computational linear algebra.
Hugging Face models are all you need for “vanilla” image classification
Portfolio website and blog running on hugo.
Portfolio and blog running on Hugo pages.
My personal website & portfolio.
Long running tasks in Dash using RQ
Data Structures and Algorithms in C++.
DS case interview questions alongside frame-worked answers. Questions sourced from various resources, primarily FAANGs.
List of Data Science Cheatsheets to rule the world
Climate ecology analyses for my conference proceedings at the SICB '21 Meeting (Society for Integrative and Comparative Biology).
ESC-50: Dataset for Environmental Sound Classification
Experiments applying chat templates to generative language model evaluations.
Docker backend running on flask, mysql, and redis queue. Intended as lightweight boilerplate.
A Great Collection of Deep Learning Tutorials and Repositories
Deep RL for unsupervised hyperspectral band selection.
All data and analyses to reproduce my ice material science research, as published in Penn Science: Furman and Goldsby, 2021.
Build a Website by practicing HTML, JSON, and XML.
you want it, you got it
Do open-sourced LLMs reason as well as closed-sourced ones?