- New York, NY
-
19:16
(UTC -05:00) - scottpitcher.github.io
- in/scottpitcher1
- https://medium.com/@scottpitcher_
- https://www.kaggle.com/scottpitcher
Highlights
- Pro
Stars
(In progress) Due to the rise of recent queries into the ethical implications of LLM usage by everyday users, this project will serve to analyse the sentiment of these models (GPT, Claude, Gemini).β¦
Personal project more for learning than portfolio
Automatically create podcast trailers from podcast audio / transcript data to facilitate quick browsing of podcasts and promote engagement
E-commerce Marketing Analytics and Optimization
For my R Programming course, we were tasked with creating an R package. I chose to create a package centered around functions to calculate one's carbon usage. Rough estimates were used for estimation.
A collection of miscellaneous assignments from my R Programming class.
Building Apps with LLMs
Statistical analysis using machine learning models (XGBoost) to uncover trends in the New York housing market!
Using CNNs in PyTorch to classify clothing images.
Dive deeper into LLMs via creating a micro-LLM decoder from scratch to best understand the architecture.
Developing a Reinforcement Learning model to learn to play Pokemon Platinum, integrating this into the code through a desktop emulator such as DeSmuME. Will then utilise RLHF (Reinforcement Learninβ¦
Using the MovieLens dataset, will create a customer recommendation system from scratch using PyTorch.
(In-progress) Finetuning OpenAI's GPT-3.5-Turbo as a base model on open-source data about the Tampa Bay region to create a chatbot specializing in information on the area!
Develop a system that personalizes music recommendations for users and analyzes their engagement and retention.