ML Lifecycle -Data Collection and Preparation
Below are the steps for Data Collection and Preparation in the Machine Learning Lifecycle Identify Data Requirements Data Collection Labeling…
ML Lifecycle – Deploying Model for Inference
After training and tuning a machine learning model, it’s time to deploy it for inference. There are several deployment options,…
ML Lifecycle – Training, Tuning, Evaluate Model
Training the Model Running Experiments Hyperparameters Using SageMaker for Training Iterative Process SageMaker Experiments Automatic Model Tuning (AMT) This iterative…
ML Lifecycle – Define the Business Problem
Identify the specific business problem to solve. Establish clear business objectives and success criteria to evaluate the model. Align stakeholders…
AWS Pre-trained AI Services
Before building a custom AI model, check if there’s an existing service available. AWS offers pre-trained AI services accessible via…
ML Problem Types
1. Supervised Learning: 2. Unsupervised Learning: Supervised Learning Details Classification: Regression: Unsupervised Learning Details Clustering: Anomaly Detection:
Practical Use Cases for AI
AI can be applied in a variety of business and operational scenarios. However, it is important to understand where AI…
Model Performance, Bias, and Fairness in Machine Learning
1. Model Performance Issues 2. Bias in Machine Learning 3. Ensuring Model Fairness Key Terms to Remember:
Model Training and Machine Learning Styles
1. Model Training & Deployment 2. Inference Options 3. Machine Learning Styles 4. Key Differences in Learning Styles Key Terms…
Deep Learning and Generative AI Concepts
1. Deep Learning: 2. Deep Learning vs. Traditional Machine Learning: 3. Generative AI: