Author: John

Defintion Explainable Artificial Intelligence (XAI) is a field of AI to provide transparency and details on the decision making process of the AI system. Interpretability

To be added

Problem In production ML, it’s not done after training and deploying the model. Blackbox Loss (ex: cross entropy and mse) Accuracy or error Ex: Tensorboard

Problem Large ML model might be difficult to be deployed because of deployment constraint (edge/mobile devices). Training a small model on raw data might not

Problem When training a large model with multiple workers/accelerators, they might be idle when the data ingestion is not fast enough to catch up with

Problem A model is too large to fit on one machine. Space – Too many weights to fit in memory Time – Too many training

Problems of high dimension Many ML algorithm relies on distances to compute similarity between samples Curse of dimensionality – as number of dimension increases, distances

What is hyper-parameter tuning? Since variables of the model that cannot be learned by the learning algorithm (via gradient descent) still need to be optimized

There are two broad kind of ML problems: supervised and unsupervised learning. Supervised Learning – each record has both feature and label (X and Y)

We discuss a few ways of doing feature selection in ML. Unsupervised method Check the linear correlation among the features (without the label) Remove features