review_update_karthik_2

Author: sdash77

guide/14-deep-learning/how_PSETAE_works.ipynb

@@ -157,7 +157,7 @@
     "\n",
     "- The pre-trained word embedding model used in the original mode is replaced by PSE's spectral embedding.\n",
     "- The positional encoder uses the first obervation or date to calculate number of days to other dates. This helps the model to take in account the variance in temporal observations.\n",
-    "- As the goal was to encode the whole time-series into single embedding, rather then output for each element of sequence. Hence, Query tensors generated by the each attention heads are pooled into single master query."
+    "- The goal is to encode the whole time-series into single embedding, rather then generate one for each element of sequence. To achieve this, query tensors generated by the each attention heads are pooled into single master query."
    ]
   },
   {