Pinned Loading

1. Speaker-Classification Speaker-Classification Public

   Performing classification of speakers in speech signals. The model has achieved a remarkable accuracy rate of 97.06% on the task, ranking in the top 6% out of 1000 teams.

   Jupyter Notebook

2. Question-Answering Question-Answering Public

   Utilizing BERT for the downstream question answering task resulted in the model achieving a notable accuracy rate of 84.18%. The model ranks in the top 6% out of 1000 teams.

   Jupyter Notebook

3. Machine-Translation Machine-Translation Public

   Performing English to Chinese machine translation resulted in the model achieving a notable bilingual evaluation understudy (BLEU) score of 29.36.

   Jupyter Notebook

4. Anime-Face-Generation Anime-Face-Generation Public

   Generating anime faces using a generative adversarial network (GAN). The model has been recognized as the best example among 1000 students, showcasing a remarkable Frechet inception distance score …

   Python

5. Adversarial-Attack Adversarial-Attack Public

   Executing non-targeted attacks using the Fast Gradient Sign Method (FGSM) and Iterative Fast Gradient Sign Method (I-FGSM) attack algorithms on proxy networks resulted in the attacked model achievi…

   Jupyter Notebook

6. MySQL-clustering MySQL-clustering Public

   Implementing MySQL Loadable Function for clustering algorithm including kmeans, hierarchical clustering, and DB scan, which allows these clustering methods can be used right in the MySQL.

   C++