Repository for the Machine Learning Based Systems Design course, offered as an elective in the Computer Engineering undergraduate program at UFRN.

Week 01

• Course Outline
  • GitHub Education Pro: Get access to the GitHub Education Pro pack by visiting GitHub Education
  • 📖 Learning Resources
    • GitHub Learning Game: Check out the interactive Git learning game at GitHub Learning Game
  • Michael A. Lones. How to avoid machine learning pitfalls: a guide for academic researchers Arxiv
• Visualizing Gradient Descent
  • Understanding and visualizing the five core steps of the Gradient Descent algorithm:
    1. initializing parameters randomly
    2. performing the forward pass to compute predictions
    3. calculating the loss
    4. computing gradients with respect to each parameter
    5. updating the parameters using the gradients and a predefined learning rate.

Week 02

• Rethinking the Training Loop (Part I)
  • From data deneration to make predictions
    • Implement a clear train() function with custom dataset and DataLoader.
    • Apply mini-batch gradient descent and track performance.
    • Add persistence: save checkpoints and enable training resumption/deployment.
  • Going Classy
    • Build a dedicated training class with a well-structured constructor.
    • Use proper method scoping (public/protected/private).
    • Consolidate earlier code into the class.
    • Run the full pipeline through the class interface.

Week 03

• Inside AirBnB Case Study: Multivariate Regression Problem.

Week 04:

• Rethinking the Training Loop (Part II)
  • A simple classification problem:
    • build a model for binary classification
    • understand the concept of logits and how it is related to probabilities
    • use binary cross-entropy loss to train a model
    • use the loss function to handle imbalanced datasets
    • understand the concepts of decision boundary and separability
  • Challenge (bonus: 2.5 points)

Week 05

• Machine Learning and Computer Vision - Part I
  • From a shallow to a deep-ish clasification model:
    • data generation for image classification
    • transformations using torchvision
    • dataset preparation techniques
    • building and training logistic regression and deep neural network models using PyTorch
    • focusing on various activation functions like Sigmoid, Tanh, and ReLU

Week 06

• Machine Learning and Computer Vision - Part II
  • Kernel
  • Convolutions
  • In this lesson, we’ve introduced convolutions and related concepts and built a convolutional neural network to tackle a multiclass classification problem.
    • Activation function, pooling layer, flattening, Lenet-5
    • Softmax, cross-entropy
    • Visualizing the convolutional filters, features maps and classifier layers
    • Hooks in Pytorch

Week 07

• Machine Learning and Computer Vision - Part III
• Rock, Paper and Scissors:
  • Standardize an image dataset
  • Train a model to predict rock, paper, scissors poses from hand images
  • Use dropout layers to regularize the model

Week 08

• Machine Learning and Computer Vision - Part III Cont.
• Rock, Paper and Scissors:
  • Learn how to find a learning rate to train the model
  • Understand the use of adaptive learning rates