• 0 Open
    0 Closed
    Updated 2024-07-31 12:00:15 +09:00
    No due date

    There are a lot of different type of layer in NN.
    Those are physically identical? What's their topological difference?

    • Fully connected layer
    • Attention layer
    • ...
  • 0 Open
    0 Closed
    Updated 2024-07-31 11:37:25 +09:00
    No due date

    How do other people think about model train efficiency?
    Just Number of resource x running time?
    Let's investigate about it and fix the target metric.

  • 0 Open
    0 Closed
    Updated 2024-07-31 11:57:54 +09:00
    No due date

    How can I physically abstractify loss function as global potential?

    • Cross entropy
    • RMSE
    • ...
  • 0 Open
    0 Closed
    Updated 2024-07-31 12:02:19 +09:00
    No due date

    What's physical meaning of sharing weight gradient?
    What happen when I apply different form of data sharing?

  • 0 Open
    0 Closed
    Updated 2024-07-31 11:50:07 +09:00
    No due date

    Clarify the random walk behavior when train use

    • SGD optimizer
    • Adam optimizer
    • ...

    More over, can we find that which optimizer can make agent as active particle?

  • 0 Open
    0 Closed
    Updated 2024-07-31 11:35:51 +09:00
    No due date

    To test train method automatically, we need to build the train protocol.
    It should satisfy followings.

    • Connect to AWS instance / run training
    • Abstraction of model and training
    • Evaluate train result