Skip to content

CMPSC-310-AI-Spring2023/activity15_transformers-Burnytoast

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Review Assignment Due Date

CMPSC 310 Activity 15

Deadline: April 12 by 9:50am

Assignment

For this activity follow Neural machine translation with a Transformer and Keras.

Submission

Submit completed Colab notebook showing generated output.

Andrew: I tried running the Colab twice and my project crashed in the training after hours of training.

Data: The data in this sense is natural language as we understand it. The computer could have a difficult time making sense of our way of speaking, as the way we derive meaning isn't easily injected into an algorithm that can just churn out those results. We have a deep, intricate understanding of verbigae, possession, the items that these objects act on (Direct Objects).

Preprocessing & transformer: Using the transformers, the algorithm is able to make parallel relations between points in the data, making it more "efficient" in a sense than CNN or RNN. RNNs and CNNs can't run things sequentially like transformers can, making them ideal for natural language processing.

About

activity15_transformers-Burnytoast created by GitHub Classroom

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published