fix: Fix ONNX link (#2035)

docs/Explore Algorithms/Deep Learning/ONNX.md

@@ -71,7 +71,7 @@ available models, optionally filtering by name or tags.
     | softMaxDict       | A map between output DataFrame columns, where the value column will be computed from taking the softmax of the key column. If the 'rawPrediction' column contains logits outputs, then one can set softMaxDict to `Map("rawPrediction" -> "probability")` to obtain the probability outputs.                                                                                                                                                                                                   | None                                           |
     | argMaxDict        | A map between output DataFrame columns, where the value column will be computed from taking the argmax of the key column. This parameter can be used to convert probability or logits output to the predicted label.                                                                                                                                                                                                                                                                           | None                                           |
     | deviceType        | Specify a device type the model inference runs on. Supported types are: CPU or CUDA. If not specified, auto detection will be used.                                                                                                                                                                                                                                                                                                                                                            | None                                           |
-    | optimizationLevel | Specify the [optimization level](https://onnxruntime.ai/docs/resources/graph-optimizations.html#graph-optimization-levels) for the ONNX graph optimizations. Supported values are: `NO_OPT`, `BASIC_OPT`, `EXTENDED_OPT`, `ALL_OPT`.                                                                                                                                                                                                                                                           | `ALL_OPT`                                      |
+    | optimizationLevel | Specify the [optimization level](https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html#graph-optimization-levels) for the ONNX graph optimizations. Supported values are: `NO_OPT`, `BASIC_OPT`, `EXTENDED_OPT`, `ALL_OPT`.                                                                                                                                                                                                                                                           | `ALL_OPT`                                      |
 
 4. Call `transform` method to run inference on the input DataFrame.