# Week 3- Attention Model: attention formula may be misleading **URL:** \ **Category:** Sequence Models\ **Tags:** coursera-platform\ **Created:** [August 26, 2021, 3:11pm UTC](https://community.deeplearning.ai/t/week-3-attention-model-attention-formula-may-be-misleading/31397 "2021-08-26T15:11:02Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![shervin](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/shervin/32/1901_2.png) [@shervin](https://community.deeplearning.ai/u/shervin)\ **Post date:** [August 26, 2021, 3:11pm UTC](https://community.deeplearning.ai/t/week-3-attention-model-attention-formula-may-be-misleading/31397/1 "2021-08-26T15:11:02Z")
Hello friends, I the ‘Attention Model’ video at time 6:11, a formula is presented for calculating attention variable (alpha\). Although the formula is understandable, it can also be confusing, since the parameter t’ (t-prime) which is used as an index counter in the denominator, is the same as the one which is written on the left-hand side and also the numerator, and the two do not seem to be related to each other. Maybe using some different variable like “j” is more suitable to be representative of the summation index. ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [August 26, 2021, 9:37pm UTC](https://community.deeplearning.ai/t/week-3-attention-model-attention-formula-may-be-misleading/31397/2 "2021-08-26T21:37:09Z")
Thanks for your suggestion. ---
**Author:** ![shervin](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/shervin/32/1901_2.png) [@shervin](https://community.deeplearning.ai/u/shervin)\ **Post date:** [August 27, 2021, 8:50am UTC](https://community.deeplearning.ai/t/week-3-attention-model-attention-formula-may-be-misleading/31397/3 "2021-08-27T08:50:06Z")
That’s my pleasure 🙏