The future of machine learning will not be defined only by larger models. Much of the progress will come from learning with less supervision, automating model design, running models closer to users and making them accountable when their decisions affect society.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
For this exercise, I developed a recommender system in stages, from simple baselines to biased matrix factorisation, before asking whether SHAP explanations make individual predictions more understandable. What stood out was that better rating prediction did not automatically produce better top-10 ranking.
I used CNN Explainer to follow two images through a small convolutional neural network: an espresso, which matches one of the model's trained classes, and a sunflower, which does not. Comparing them exposed a basic limitation of image classifiers: a model can only choose from the labels and examples represented in its dataset.
This reflection covers my initial post, peer responses, feedback and summary for the second collaborative discussion in the Machine Learning module, which focused on AI writers, human oversight and responsible use.
I compared classification and regression parameter choices using held-out test data.
My CNN object-recognition notebook covers the model setup, training results, a test prediction and the limitations of using CIFAR-10 for image classification.
Wall's article made me think about facial recognition less as a model-accuracy problem and more as a deployment problem: what happens when an organisation treats a CNN score as objective evidence? A convolutional neural network can return a probability or similarity score, but that score does not, by itself, establish a person’s identity. In a photo app, a wrong match can merely be irritating; but in policing, border control, or military use, it can expose someone to surveillance, exclusion, arrest, or harm (Wall, 2019).
Using Yu et al. (2024) as a comparison framework, I consider how conventional machine learning and deep learning could be evaluated for production-line visual inspection, and how their decisions could be explained to the people expected to act on them.
In this short exercise, I explored how gradient descent reduces a cost function by repeatedly updating model parameters.
I worked through three neural network notebooks: a simple perceptron, a perceptron trained for the AND operator, and a multilayer perceptron for a more complex non-linear problem.
Google Colab notebook: Open the hybrid Airbnb demand notebook · Raw Notebook: Download .ipynb
I wanted to find out whether combining text, location context and ordinary listing details could predict Airbnb demand more effectively than structured data alone. I tested this using the Airbnb NYC 2019 dataset, with 48,884 listings remaining after invalid rows were removed. For this experiment, I defined “high demand” as at least 1.58 reviews per month, the upper quartile of the dataset. This is a proxy for demand rather than a measure of confirmed bookings or occupancy, so the results should be interpreted as predictions of review activity.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
My Colab notebook applies the same k-means clustering process to three datasets: Iris, Wine, and WeatherAUS. Here, I explain the methodology behind it.
I watched two animations of the k-means clustering algorithm to see how it repeatedly assigns data points to clusters and updates their centroids.
I used a small table of pathological test results to calculate the Jaccard distance and corresponding Jaccard similarity coefficient for three pairs of individuals.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
This portfolio activity investigates the relationship between a country or entity's mean population and its mean total GDP across the years 2001-2020. The analysis uses two World Bank datasets, global_gdp.csv and global_population.csv, and applies descriptive analysis, Pearson correlation, log-scale visualisation, and simple linear regression.
The first collaborative discussion in the Machine Learning module focused on Industry 4.0, Industry 5.0, digital infrastructure and data-driven operational resilience. Here, I reflect on my initial post, two peer responses and the final summary.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
The Airbnb NYC 2019 dataset is useful for exploring listing-level patterns, but it has one important limitation: it does not contain direct demand measures. There are no actual booking counts, occupancy rates, revenue figures, or guest ratings that can be used as a clean target variable.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
I expanded a basic correlation and regression example into a set of controlled experiments exploring how dataset properties affect statistical results.
Google Colab notebook: Open in Google Colab · Raw Notebook: Download .ipynb
I used exploratory data analysis (EDA) to assess whether the Auto MPG dataset was suitable for machine learning and to identify key uncertainties before modelling.