Scribd
Upload
10 views2 pages

Ai Notes ch2

Chapter 2 of 'Artificial Intelligence 101' focuses on Machine Learning (ML) fundamentals, defining ML as a field that enables computers to learn from experience. It outlines key paradigms such as supervised, unsupervised, and reinforcement learning, along with typical workflows and common algorithms. The chapter emphasizes the importance of data preparation, evaluation, and best practices to avoid pitfalls in ML applications.

Uploaded by

Xenia Wilke
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views2 pages

Ai Notes ch2

Chapter 2 of 'Artificial Intelligence 101' focuses on Machine Learning (ML) fundamentals, defining ML as a field that enables computers to learn from experience. It outlines key paradigms such as supervised, unsupervised, and reinforcement learning, along with typical workflows and common algorithms. The chapter emphasizes the importance of data preparation, evaluation, and best practices to avoid pitfalls in ML applications.

Uploaded by

Xenia Wilke
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Artificial Intelligence 101 – Chapter 2

Machine Learning Fundamentals


-----------------------------

Key Objectives
• Differentiate AI and Machine Learning (ML).
• Survey primary ML paradigms and algorithms.
• Appreciate common pitfalls and best practices.

1. What Is Machine Learning?


Arthur Samuel (1959): “Field of study that gives computers the ability to learn without
being explicitly programmed.”
– Systems improve on a task T with experience E measured by performance P.

2. Main Paradigms
• Supervised Learning – labeled data (classification, regression).
• Unsupervised Learning – find structure (clustering, dimensionality reduction).
• Reinforcement Learning – agents learn via reward feedback.
• Semi■supervised & Self■supervised – leverage unlabeled data.

3. Typical Workflow
1) Problem Definition
2) Data Collection & Cleaning
3) Feature Engineering
4) Model Selection & Training
5) Evaluation (train/validation/test splits, cross■validation)
6) Deployment & Monitoring

4. Common Algorithms
– k■Nearest Neighbors
– Linear & Logistic Regression
– Decision Trees & Random Forests
– Support Vector Machines
– Gradient Boosting (XGBoost, LightGBM)
– Neural Networks & Deep Learning

5. Key Concepts
• Overfitting vs. Underfitting
• Bias■Variance Trade■off
• Regularization (L1, L2, dropout)
• Hyperparameter Tuning
• Performance Metrics (accuracy, precision, recall, F1, ROC■AUC)

6. Tools & Libraries


– Python (NumPy, pandas, scikit■learn)
– TensorFlow, PyTorch, JAX
– MLOps: MLflow, Kubeflow

Quick Summary
ML empowers computers to learn patterns from data. Mastery involves understanding
algorithms, diligent data preparation, and rigorous evaluation to avoid misleading
results.

You might also like