Introduction to Machine Learning [MAK]

Beginner's session on Machine Learning for students at Makerere University

Transcript

1. Intro to Machine Learning Wesley Kambale @weskambale kambale.dev
2. • Machine Learning Engineer with 3 years of experience • Community Builder for 3 years • Explore ML Facilitator with Crowdsource by Google for 2 years • Google Dev Library Author Profile Interests Experience • Research in TinyML, TTS & LLM
3. What You Need to Know/Have? - Knowledge of Python, R, Java, etc - Basic mathematical knowledge (probability and statistics) - Notebook (Google Colab or Jupyter) - Basic data analytics knowledge (MS Excel, Power BI) Pre-requisites
4. Machine Learning… What is Machine Learning? Machine learning (ML) is a subfield of artificial intelligence (AI) that enables computers to learn from data to make predictions and identify patterns. Computers traditionally rely on explicit programming. Machine learning is programming computers to optimize a performance criterion using example data or past experience
5. Traditional Programming Machine Learning Computer Data Program Output Computer Data Output Program
6. Machine Learning… Types of Machine Learning? • Supervised learning – Training data + desired outputs (labels) • Unsupervised learning – Training data (without desired outputs) • Semi-supervised learning – Training data + a few desired outputs • Reinforcement learning – Rewards from sequence of actions
7. Supervised learning What is Supervised Machine Learning? Used when the training data includes labeled examples. The algorithm attempts to find the relationship between the input features (independent variables) and the output (dependent variable), which is known as the "ground truth". Common examples of supervised learning include classification (determining the class of an object based on its features) and regression (predicting a continuous value).
8. SL: Regression Given (x1, y1), (x2, y2), ..., (xn, yn) Learn a function f(x) to predict y given x – y is real-valued == regression
9. SL: Classification Given (x1, y1), (x2, y2), ..., (xn, yn) Learn a function f(x) to predict y given x – y is categorical == classification
10. Unsupervised learning What is Unsupervised Machine Learning? Used when the training data is unlabeled. The algorithm must identify patterns and structure in the data on its own. Common examples of unsupervised learning include clustering (grouping similar data points) and dimensionality reduction (reducing the number of features in the data).
11. Unsupervised Learning Given x1, x2, ..., xn (without labels) Output hidden structure behind the x’s – E.g., clustering
12. Unsupervised Learning
13. Semi-supervised learning What is semi-supervised Machine Learning? It uses a combination of labeled and unlabeled data: The labeled data provides the grounding for the model, teaching it basic concepts and the structure of the problem. The unlabeled data adds additional information and helps the model learn more complex relationships and patterns.
14. Reinforcement learning What is reinforcement Machine Learning? An agent learns through trial and error in an environment. The agent takes actions, observes the outcome, receives a reward (positive or negative), and uses this feedback to improve its future choices. This allows the agent to learn without explicit instructions and adapt to changing environments.
15. Take an example For humans, it is hard to know which is 2
16. Getting Started Shall we?
17. The libraries you need What next? Pandas NumPy Matplotlib & Seaborn Sci-Kit Learn & TensorFlow
18. ML in a Nutshell In a simple way… - Tens of thousands of machine learning algorithms - Hundreds new every year - Every ML algorithm has three components: Representation Optimization Evaluation
19. Representation Numerical functions: Linear regression, neural networks, support vector machines Symbolic functions: Decision trees Instance-based functions: Nearest-neighbor, case-based Probabilistic Graphical Models: Naïve Bayes, Bayesian networks, Hidden-Markov Models Markov networks
20. Search/Optimization Gradient descent: Perceptron, Backpropagation Dynamic Programming: HMM Learning Divide and Conquer: Decision tree induction, Rule learning Evolutionary Computation: Genetic Algorithms (GAs) Genetic Programming (GP) Neuro-evolution
21. Evaluation Accuracy Precision and recall Squared error Likelihood Cost / Utility Margin Entropy
22. ML in Practice Understand domain, prior knowledge, and goals Data integration, selection, cleaning, pre-processing, etc. Learn models Interpret results Consolidate and deploy discovered knowledge
23. Machine learning is the future - Robert John, GDE - ML & Google Cloud
24. Thank you! Wesley Kambale @weskambale kambale.dev