This repository is the implementation of the paper: ViT2 - Pre-training Vision Transformers for Visual Times Series Forecasting. ViT2 is a framework designed to address generalization & transfer learning limitations of Time-Series-based forecasting models by encoding the time-series to images using GAF and a modified ViT architecture.

Final project for Visual Analytics course at Aarhus University (S2023)

Master's thesis - Assessment of cognitive load in extreme environment

practice on timeseries data transforming on Financial Vision Topics

🧠 Reduce cognitive load in coding to enhance understanding and efficiency. Contribute to a clear, practical guide for improving code comprehension.

PyTorch accelerated GAF transform

A comparative analysis of MLP and CNN (GAF) models for time series forecasting on AAPL stock, exploring stationarity, log returns, and fractional differencing.

An investigation into the application of Deep Learning architectures (MLP, LSTM, and CNN via Gramian Angular Fields) to predict Bitcoin directional returns, focusing on a rigorous forensic analysis of data leakage.