This is the Course 4 of 5 in the Deep Learning Specialization, provided by Andrew Ng (DeppLearning.ai). After 51 videos (total about 7.5 hours) and 8 programming assignments (TensorFlow) I was able to understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more.
The course taught me how to implement the foundational layers of CNNs (pooling, convolutions) and how to stack them properly in a deep network to solve multi-class image classification problems.
It introduced me to some powerful practical tricks and methods used in deep CNNs, straight from the research papers:
- Residual Network (ResNet)
- Inception network
- MobileNets
- applying transfer learning to deep CNN
Through this course I learned one of the hottest (and most challenging!) fields in computer vision object detection:
- recognition
- detection
- semantic segmentation
The end of this course taught me how to apply CNNs to multiple fields, including:
- neural style transfer to generate art
- Facial Recognition System to recognize faces
Credentials: