PlantVision🌿(an ambitious personal project l am working on) is an end-to-end deep learning system for detecting and classifying different kinds of plant diseases based on their leaves It leverages MLOps best practices, and will be deployed for offline mobile use and web through APIs https://github.com/MDeus-ai/PlantVision So l realized that instead being trapped in tutorial hell, why don't l just learn by building actual real world end-to-end machine learning systems, and to be honest, l enjoy it, l am learning stuff no tutorials would have taught me

I have been in a situation where l needed to carry out a statistical test on a one-hot-encoded nominal variable. It turns out that one-hot-encoding such variables dramatically increases the dimensionality of the dataset. The challenge l always face is that l don't really know how to carry out a statistical test of such a variable in its one-hot-encoded form since it introduces more columns for this variable. I thought of doing univariate tests on each column but l am not sure

Is there any possible way one can speed up parameter fine tuning of ML algorithms likes svms, random forests and so on. I always struggle when it comes to this step, its just so time consuming mostly when am dealing with a large parameter space🤧. Is there any way l can parallelize this process, any gpu support for this, any libraries specifically for this 🤲🏾?

Hello everyone! I'm a first year student at BITS-RMIT joint education program and I am pursuing my bachelor degree in electronics and communication engineering . I'm fairly new to programming world and I want to pursue ai engineering in future. If anyone has any tips and recommendations for a student like me who wants to use spare time at university to study ai then please do share.

Do you think Data scientists and ML engineers will soon be replaced by AI?