Hello everyone, I am currently an AI intern. I am taking the Deep Learning Specialization course and working on an internship project involving liveness detection. I have completed about 10 projects on topics such as CNN, ResNet, basic GANs, YOLOv8, Pretrained GPT-1, and translation using seq2seq. For the liveness detection project, I have found that there is limited GitHub documentation on the subject, with most resources focusing on preprocessing and training models like MCCNN, ViT, and Hybrid CNN and RNN.
My issue is that there are quite a few models to choose from, and I hope this internship will provide valuable experience to help me become an AI Engineer in the future. I am currently approaching the models by understanding their components and coding them, but I find this process time-consuming. To determine the model I need, should I focus on understanding and coding the model completely, or is it sufficient to just understand the model (i.e., its structure and characteristics) by asking ChatGPT and reading some documentation?
For example, with the Hybrid CNN and RNN model, since I already have a base understanding of CNNs, do I need to code the RNN component as well, or can I directly learn about the Hybrid CNN?
My Knowledge and Experience:
- Python basics: Immediate. Understanding of processing in files and working with classes.
- Math: Understanding of probability and matrices.
- Machine Learning (ML): Familiar with about 7-8 different techniques, with a primary focus on Linear and Logistic regression (to serve Deep Learning purposes).
- Deep Learning (DL): Understanding of 7 regularization techniques and a few normalization methods. Project experience mainly in computer vision (CV).
Completed approximately 10 projects involving CNN, ResNet, UNet, basic GANs, YOLOv8, Pretrained GPT-1, and translation using seq2seq.
- Badges
- Science topic
- Similar topics
- Chemistry
- Sulfites
- Inorganic Chemistry
- Inorganic Chemicals
- Salts