Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SuperLinear: A Mixture of Experts Time Series Forecasting Model
|
| 2 |
|
| 3 |
SuperLinear is a novel time series forecasting model that employs a Mixture of Experts (MoE) architecture to achieve superior performance across various forecasting tasks. The model routes inputs to the most relevant experts based on frequency-domain analysis using FFT-based gating networks.
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- time-series
|
| 6 |
+
- mixture-of-experts
|
| 7 |
+
- forecasting
|
| 8 |
+
- pytorch
|
| 9 |
+
- fft
|
| 10 |
+
model-index:
|
| 11 |
+
- name: SuperLinear
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
# SuperLinear: A Mixture of Experts Time Series Forecasting Model
|
| 17 |
|
| 18 |
SuperLinear is a novel time series forecasting model that employs a Mixture of Experts (MoE) architecture to achieve superior performance across various forecasting tasks. The model routes inputs to the most relevant experts based on frequency-domain analysis using FFT-based gating networks.
|