We can help to build and train network models (machine learning) for various purposes.
Work experience & Applied projects:
Facial recognition and emotion analysis program for social media
Independent Project
● Motivation and research direction: With the development of Internet entertainment, more and more people have become video bloggers. The viewer’s evaluation is important to them. However, due to people’s preferences and emotional factors, it’s difficult to generally tell their true feelings from the videos. So people’s facial expressions when watching a video are the most intuitive and true evaluation of a video. Also, for applying this function, we only need to ask for the agreement of viewers. Compared with text comments, that will save their time and make people willing to help.
Cover classification program for library assistants
In-class Kaggle competition
● Managing and setting up the database of training samples, regularizing and normalizing data. ● Building multiple ML models and doing research, intended to optimize the performance of the program. Layer structure design using Keras and Tensorflow library.
Animal breeds identification program for AI assistant
Teamwork on google colab
● Designing the structure and giving constructive opinions, imitating the combination of brain neurons to arrange and combine multiple CNN models. Therefore, complex tasks can be completed through simple models.
● Building and training CNN models using Python/Numpy, doing research on different models and comparing the performance.