| 39 | | Goals: |
| 40 | | Summary: |
| 41 | | - Created and Trained a ‘Small’ and ’Large’ Neural Networks |
| 42 | | - Compared their performances on the CIFAR10 dataset |
| 43 | | - Established connection between two nodes |
| 44 | | - Communicated test data between nodes to compare accuracy and delay between our NN models |
| 45 | | - Need to serialize by bytes instead of transferring as strings |
| 46 | | - Had a discussion on various research papers related to our project |
| 47 | | Next Steps: |
| 48 | | - Send the data as bytes instead of strings |
| 49 | | - Calculate the times for transfer & processing |
| 50 | | - Read more papers related to stuff about early exit and edge cloud computing |
| 51 | | - Divide data into “chunks” for faster and more efficient transmission |
| 52 | | - Design experiments to test different architectures and implementations of Early Exiting and Split Computing |
| 53 | | - Track and add Age of Information Metrics |
| 54 | | Presentation links: |
| 55 | | - Link - Lakshya |
| 56 | | - Link - Shreya |
| 57 | | - Link - Haider |
| 58 | | - Link - James |
| 59 | | - Link - Tanushree |
| 60 | | |