What courses do you want to see the deeplearning.ai team build next?
I see a lot of people are interested in RL but I think there are many other important things that needs to be covered first. RL still has very very limited applications in the real world. It is good to explore but the applications are very limited at this point in time. Here are few things that I think are more important to cover:
- Advanced DNN architectures: MobileNets(v1 and v2), ResNeXt, WideResNets, etc.
- Advanced object detection: SSD, YOLOv3, RetinaNet. How it is implemented in SDCs?
- Segmentation: UNets, DeepLab(v1, v2 and v3), DenseNet. Things in medical imaging and self driving cars
- Optimization algorithms: Learning rate finder, Cyclic learning rates, One cycle policy, super-convergence, AdamW
Recommendation engines using Deep learning
NLP and Speech: BERT, UMLfit, etc.
Hello everyone, I really want to thank you a lot, the whole deeplearning.ai team for teaching us deep learning, I can't express my thankfulness for your amazing work, providing us with the tremendously helpful courses on deep learning.
a - Advanced Deep Learning In computer vision:
- Image Classification
- Image Classification With Localization
- Object Detection
- Object Segmentation
- Image Style Transfer
- Image Colorization
- Image Reconstruction
- Image Super-Resolution
- Image Synthesis
- Image generation
b- Advanced NLP in Deep Learning:
- Speech recognition
- Machine translation
- Object Segmentation
- Language modeling
- Semantic matching
c- I wish also to provide us with a course about how to join a Kaggle competition, so that every group of learners will be able to build a strong team to join competitions, and by that we may have a chance to share our experience as deeplearning.ai online fans at Kaggle.
Graph Neural Networks (GNN)
There is little information about this topic, although it has a lot of applications as many real world problems can be translated to graphs.
Most work can be found on scientific article, but there is almost no implementation tutorial, popular science articles or courses.
It seems like the field is still changing a lot with several competing model architecture, but I believe this will be a growing topic, and a course on the basics would be useful.
First Thank you very much for providing Education through coursera and deeplearning.ai to every corners of world. 🙂
I would also want to see these things in upcoming courses of our deeplearning.ai team:
2) Generative adversarial networks
3) Reinforcement learning
4) Self driving Car Specialization
5) Full Robotics and Raspberry pi specialization , (like Professor, Andrew told he used reinforcement learning to make AI drone to fly, took 1 year to make, hope he would help me to learn it) also added IOT
Thanks @andrea to give our thoughts.
This deeplearning.ai , I am grateful forever to give opportunities specially my favorite professor Andrew ng .