Shopping Cart

No products in the cart.

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

Congratulations,

You’ve made it to the final stage of this course, and that alone is a remarkable achievement.

Let’s look back at what you have accomplished.

  • You started by understanding AI, Machine Learning, and Deep Learning.
  • You explored key machine-learning concepts: datasets, model training, evaluation, overfitting, optimization, and hyperparameter tuning.
  • Using real-world data, you implemented core machine learning algorithms, such as linear and logistic regression, decision trees, K-nearest neighbors, and support vector machines.
  • You built your own neural network from scratch, learning how they operate, train, and adapt to grading descent and backpropagation.
  • You mastered data handling and preprocessing: cleaning, normalizing, engineering features, and performing exploratory data analysis.
  • You worked with PyTorch, bringing everything together into a streamlined machine-learning pipeline, training, evaluating, and saving models just like a real-world machine-learning engineer.
  • You explored advanced deep-learning architectures, including convolutional neural networks for image processing and recurrent neural networks for sequential data.
  • You completed the capstone project, applying your knowledge to a real-world dataset, making sense of big data, training models, and drawing insights from AI power predictions.

So what’s next?

Your journey continues.

While this course has provided you with a strong foundation, machine learning is fast-evolving. The models you trained today are just the beginning. What’s coming next in AI and machine learning is truly beyond imagination. And here’s the key. Machine learning is not a plug-and-play solution. It’s not just about feeding data into a model and expecting results. It requires critical thinking, creativity, and iteration. Every dataset is different. Every problem has its challenges, and the real power of machine learning lies in your ability to ask the right questions, interpret results, and continuously refine your models.

Stay curious and keep learning. The best machine learning practitioners never stop learning. AI is evolving at an unprecedented pace, and staying ahead means exploring new models, reading research papers, experimenting with real-world data, and always asking how this can be improved.

Apply machine learning to your own problems. The best way to keep learning is by doing. Whether you’re working in engineering, science, business, or any other field, machine learning has the potential to enhance decision-making, automate processes, and unlock insights you never thought possible.

What’s coming next is unbelievable. The AI breakthroughs of today were unimaginable just a decade ago: self-learning algorithms, real-time AI systems, generative AI models… These are transforming the world in ways we are only beginning to understand. And you are now part of that movement.

So, as you move forward, keep learning, keep questioning, and keep building. The future of AI is unfolding right now, and the next breakthroughs will come from people who are willing to push the boundaries, challenge norms, and explore the ocean of possibilities that AI offers.

Thank you for being part of this journey.

We can’t wait to see what you create.

See you in the next challenge!

Back to Course

Report

Harassment or bullying behavior
Contains mature or sensitive content
Contains misleading or false information
Contains abusive or derogatory content
Contains spam, fake content or potential malware

Block Member?

Please confirm you want to block this member.

You will no longer be able to:

  • See blocked member's posts
  • Mention this member in posts
  • Invite this member to groups
  • Message this member
  • Add this member as a connection

Please note: This action will also remove this member from your connections and send a report to the site admin. Please allow a few minutes for this process to complete.

Report

You have already reported this .