Automated Bayesian model discovery for time series data
AutoTCL and Parametric Augmentation for Time Series Contrastive Learning(ICLR2024)
Linear-time sequence modeling that replaces attention's O(n²d) complexity with O(nd) summation-based aggregation. Demonstrates constraint-driven emergence: how functional representations can develop from optimization pressure and architectural constraints alone, without explicit pairwise interactions.
Demand forecasting and rebalancing analysis of urban bikeshare systems across multiple cities, using riders' patterns to inform fleet distribution strategy.
🌦️ Deep Learning RNN Project: Predict Seattle's Weather with LSTM 🌡️
Add a description, image, and links to the times-series topic page so that developers can more easily learn about it.
To associate your repository with the times-series topic, visit your repo's landing page and select "manage topics."