Could we create connections between initial layers of ANN and the later layers to facilitate capturing of “sequence” in the input? How is RNN different from following this approach?
Modifying ANN for memory
Hey @ambika11, there is lot lot of difference in both of this. The architecture, computation both are completely different. First try studying both architectures in details yourself if still unable to understand, you can connect with the TA directly over call( Call any TA from whatsapp group or can call me (8800935911)). Because the explanation in text will be way way more difficult for us TAs.
Happy Learning 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.