Why is scaling important? Because the incoming traffic will grow overtime and model will become more complex Scaling dimension Data volume Model parameters Types of
What is serving? Provide access to end users Provide service/app for interaction In ML workflow Batch inference Online Inference regularly retrained inference with the latest
Model fairness is about assess how the output of the model can impact different subgroup of the population. Tool: Tensorflow Fairness Indicators For binary and
AI has created a lot of opportunity to improve people’s lives, but also raised questions about what is the best way for the AI systems
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