I’m a seasoned developer looking to expand my knowledge in the ML/AI space. I’m currently working on a project that involves parsing information from images. While I can utilize 3rd party APIs such as those offered by Google or OpenAI, I’m interested in learning how to build and understand models that perform these tasks from the ground up.
Could you recommend any courses or resources that provide a hands-on approach to developing image parsing and information extraction models? Willing to pay $$ to learn
Image parsing and information extraction is pretty far down the maturity path, as far as builiding-your-own is concerned.
You’re in the realm of “deep learning” there. i.e. multi layer neural networks with complex models.
An intro to those topics would be found in the Deep Learning Specialization (DLS). It is a broad overview of deep learning methods. It uses more advanced Python toolsets like scikit-learn and TensorFlow.
If you have no machine learning experience, jumping straight into DLS may be too much to tackle. An intro-level course in machine learning is the Machine Learning Specialization (MLS). It introduces several sets of tools and learning concepts using using Python. It is more of a nuts-and-bolts introduction.
Both of these are paid course series offered via Coursera.
Thank you for your response TMosh - I did the Machine Learning Specialization by Andrew NG. Great course for getting an general idea however the best possible route to learn to swim in the AI space is by being thrown in the middle of this ocean. For example, I am trying to build a POC by parsing info out of real world docs and its pretty complicated. OCR only gets you to the mid point of extracting raw information.
I will checkout DLS. Thank you for your suggestion
