schnurrd
Follow
Highlights
- Pro
Stars
An annotated implementation of the Transformer paper.
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.
Unified Training of Universal Time Series Forecasting Transformers
Foundation Models for Time Series
Time-Series-Optimized Transformer for Observability
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
High-frequency statistical arbitrage
Lightweight and educational reimplementation of TabPFN https://arxiv.org/pdf/2511.03634
Exercises for the Big Data lecture at ETH Zurich (Fall 2025)
Our maintained PFN repository. Come here to train SOTA PFNs.
A Playground for Tabular Foundation Models
By combining GARCH(1,1) and LSTM model implementing predictions.
Mamba4Cast, a zero-shot time series forecasting model, achieves competitive performance and faster inference than transformer-based models by leveraging Mamba architecture and synthetic training da…
Optimised Extended LSTM for time-series forecasting
factor return calculation, mean-variance / Black&Litterman portfolio optimization, risk decomposition
Developing hybrid deep learning models by integrating Neural networks with (s,e,t)GARCH models to predict volatility in the Indian Commodity Market. We evaluate the following DNN models: Multi-laye…
A python module implementing interfaces for various public tabular priors