Am I sufficiently prepared to begin an MLOps course focused on deep learning? I’ve recently finished a Machine Learning specialization.
3 Likes
I’ll move your message to the MLOPs course discussion area. Someone who has attended the course would be better able to answer what preparation is needed.
1 Like
please
Hi @BISHWANATH_JANA,
Yes, you’re qualified to study the MLOps course. Deep Learning is only a portion of MLOps. MLOps basically will teach you about the comprehensive process of ML development. Instead of just building a deep learning project, you also learn how to deploy, maintain, and finetune the model like in real life.
It all depends on your preferences; if you want to specialize only in deep learning, I suggested the Deep Learning Specialization. If you want to understand more about the practical process of ML in business or organization services, you can go straight to MLOps courses.
I hope this helps,
Vy
4 Likes
Followup question - the FAQ for this course highly recommends completing the Deep Learning Specialization before starting. I’m interested in going straight from the ML specialization to the ML Ops course but I want to make sure I’m not missing anything I need to know in the Deep Learning Specialization. Are there any important concepts I’d be missing from the DL specialization if I skipped it?
I don’t know what’s in the MLOps course.
But DLS gives you lots more experience with TensorFlow, and topics like Convolutional NNs and Recurrent NNs.
In MLOps, there will be some assignments involving deep learning methods like Convolutional NNs. Of course, Tensorflow will be used throughout the course. However, in the assignments, it’s assumed that the deep learning model is developed and now you only learn about data analysis for finetuning, scaling, and developing a pipeline for production. Therefore, you won’t have the chance to experiment with different deep-learning models that the other specializations provide.
Taking Deep Learning Specialization is only a recommendation, you can always learn two specializations in parallel or study by yourself for the course.
1 Like