Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ can be easily fine-tuned for your target data. Refer to our [paper](https://arxi
|
|
23 |
- *UniTime (WWW 24) by 27% in zero-shot forecasting.*
|
24 |
- Zero-shot results of TTM surpass the *few-shot results of many popular SOTA approaches* including
|
25 |
PatchTST (ICLR 23), PatchTSMixer (KDD 23), TimesNet (ICLR 23), DLinear (AAAI 23) and FEDFormer (ICML 22).
|
26 |
-
- TTM (1024-96, released in this model card with 1M parameters) outperforms pre-trained MOIRAI (Small, 14M parameters) by 10%, MOIRAI (Base, 91M parameters) by
|
27 |
MOIRAI (Large, 311M parameters) by 3% on zero-shot forecasting (fl = 96). (TODO: add notebook)
|
28 |
- TTM quick fine-tuning also outperforms the hard statistical baselines (Statistical ensemble and S-Naive) in
|
29 |
M4-hourly dataset which existing pretrained TS models are finding hard to outperform. (TODO: add notebook)
|
|
|
23 |
- *UniTime (WWW 24) by 27% in zero-shot forecasting.*
|
24 |
- Zero-shot results of TTM surpass the *few-shot results of many popular SOTA approaches* including
|
25 |
PatchTST (ICLR 23), PatchTSMixer (KDD 23), TimesNet (ICLR 23), DLinear (AAAI 23) and FEDFormer (ICML 22).
|
26 |
+
- TTM (1024-96, released in this model card with 1M parameters) outperforms pre-trained MOIRAI (Small, 14M parameters) by 10%, MOIRAI (Base, 91M parameters) by 2% and
|
27 |
MOIRAI (Large, 311M parameters) by 3% on zero-shot forecasting (fl = 96). (TODO: add notebook)
|
28 |
- TTM quick fine-tuning also outperforms the hard statistical baselines (Statistical ensemble and S-Naive) in
|
29 |
M4-hourly dataset which existing pretrained TS models are finding hard to outperform. (TODO: add notebook)
|