Back to Course

AI & Machine Learning: From Scratch to Advanced Models

0% Complete
0/0 Steps
  1. The Course

    Meet the Instructors
  2. Introduction to the course
  3. Introduction
    What is Machine Learning?
    1 Quiz
  4. Universal Approximation Theorem
    1 Quiz
  5. Supervised Learning
    1 Quiz
  6. Unsupervised Learning
    1 Quiz
  7. Reinforcement Learning
    1 Quiz
  8. Historical Context and Evolution of Machine Learning
    1 Quiz
  9. Applications of Machine Learning in Naval Engineering
    1 Quiz
  10. Fundamental Concepts
    Overview
  11. Features, Labels, and Datasets
    1 Quiz
  12. Models
    1 Quiz
  13. The Machine Learning Pipeline
    1 Quiz
  14. Overfitting and Underfitting
    1 Quiz
  15. Core Algorithms
    Linear Regression
    1 Quiz
  16. Logistic Regression
    1 Quiz
  17. Decision Trees
    1 Quiz
  18. K-Nearest Neighbors (KNN)
    1 Quiz
  19. Support Vector Machines (SVM)
    1 Quiz
  20. Deep Learning Basics
    Introduction to Deep Learning
    1 Quiz
  21. Neural Networks: Structure and How They Work
    1 Quiz
  22. Neural Networks: Training
    1 Quiz
  23. What Patterns Do Networks Identify
    1 Quiz
  24. Gradient Descent
    1 Quiz
  25. Backpropagation
    1 Quiz
  26. Autodifferentiation: Simplified MLP
    1 Quiz
  27. Autodifferentiation: General MLP
    1 Quiz
  28. Autodifferentiation: Dimensionality
    1 Quiz
  29. Implementing a Simple Neural Network from Scratch: Loading the dataset
  30. Implementing a Simple Neural Network from Scratch: Polynomial fit
    1 Quiz
  31. Implementing a Simple Neural Network from Scratch: Parameter Initialization
  32. Implementing a Simple Neural Network from Scratch: Training and Results
    1 Quiz
  33. Data Handling and Preparation
    Understanding Data: Types of Data and Data Collection Methods
    1 Quiz
  34. Data Preprocessing: Cleaning and Normalization Techniques, Feature Engineering and Handling Missing Data
    1 Quiz
  35. Data Preprocessing: Practical Session
    1 Quiz
  36. Data Preprocessing Feature Engineering: Practical Session 2
    1 Quiz
  37. Exploratory Data Analysis: Visualizing Data, Identifying Patterns and Anomalies
    1 Quiz
  38. MLP Implementation with PyTorch
    Introduction to the Problem
  39. Setting Up the Environment and preprocessing data
    1 Quiz
  40. Explaining neural network with Python
    1 Quiz
  41. Building and training the model
    1 Quiz
  42. Evaluating and visualization results
    1 Quiz
  43. Conclusion
    1 Quiz
  44. Model Evaluation and Optimization
    Evaluation Metrics for Classification Models (Accuracy, Precision, Recall and F1 Score) and Confusion Matrix
    1 Quiz
  45. Evaluation Metrics for Regression Models (MAE, MSE, RMSE, R-score and MAPE)
    1 Quiz
  46. Evaluation Metrics for Deep Learning Models (Log loss, Cross Entropy Loss and Perplexity)
    1 Quiz
  47. Evaluation Metrics for Deep Learning Models: Practical Session
  48. Overfitting vs. Underfitting: Understanding Concepts and Techniques to Mitigate Overfitting
    1 Quiz
  49. Hyperparameter Tuning: Importance and Methods
    1 Quiz
  50. Hyperparameter Tuning: Practical Session
    1 Quiz
  51. Advanced Topics and Future Directions
    Introduction to Advanced Architectures: Convolutional Neural Networks (CNNs)
    1 Quiz
  52. Introduction to Advanced Architectures: Convolutional Neural Networks (CNNs) Practical Session
    1 Quiz
  53. Introduction to Advanced Architectures: Recurrent Neural Networks (RNNs)
    1 Quiz
  54. Introduction to Advanced Architectures: Recurrent Neural Networks (RNNs) Practical Session
    1 Quiz
  55. Future Trends in ML and Naval Engineering: Emerging Technologies and Potential Future Applications
    1 Quiz
  56. Ethical Considerations in AI: Use in Naval Engineering and Data Privacy and Security
    1 Quiz
  57. Final Assignment - Capstone Project
    Final Assignment (mandatory)
  58. Project Proposal and Dataset Selection
  59. Ship-D Dataset
  60. Analyze and Clean the Dataset
  61. Split the Dataset into Train, Validation, and Test
  62. Normalize the Data
  63. Define the Neural Network Architecture
  64. Train the Neural Network
  65. Test the Performance of the Neural Network
  66. Predict the Residuary Resistance for a given Hull
  67. Optional Extensions
  68. Course Materials
    Course Materials
  69. Course Survey
    Course Evaluation Survey
    1 Quiz
  70. Summary
    Wrap-up

Hello and welcome!

We are three researchers and PhD students at the University of Politécnica de Madrid. We are passionate about Artificial Intelligence and its applications in engineering.

I’m Javier Capell, an Aeronautical Engineer. My research involves computational methods, specifically computational fluid dynamics. As part of my PhD, I leveraged deep learning to develop turbulence models and help us understand such complex physics.

I am Antonio Medina, a Naval Architect. I am an experienced experimentalist, having conducted several experimental campaigns on floating systems that involve extensive data analysis. Using that data, I applied recurrent neural networks to predict the response of offshore wind turbines. This methodology enables the building of ultra-rapid models with very high accuracy.

Hi, I’m Andrés Pastor, also a Naval Architect. I work extensively with Python developing some libraries for structural analysis. I also developed a digital twin of an offshore wind turbine that uses machine learning models for prediction and simulation. It enables data-driven decisions for engineers.

Together, we bring you this comprehensive Machine Learning course designed to take you from fundamentals to advanced neural networks.

What will you learn?

  • Introduction to AI, Machine Learning, and Deep Learning, why it’s booming, and how it applies to engineering.
  • Key machine learning concepts: data handling, models, evaluation, and optimization.
  • Core algorithms: linear regression, logistic regression, decision trees, K-nearest neighbors, and support vector machines, each with real-world applications.
  • Deep Learning fundamentals: how neural networks learn; you’ll even build one from scratch.
  • Implementation with PyTorch: data preprocessing, model training, evaluation, and optimization.
  • Advanced architecture: convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
  • Practical insights and coding tips based on our hands-on experience working with large datasets and complex models.

Finally, a custom project where you will apply everything you’ve learned to either the ShipD dataset from MIT or any other dataset of your choice.

Artificial Intelligence is revolutionizing engineering. We are excited to share our knowledge and guide you through this journey to unlock the power of AI.

Welcome aboard!