AI / ML Experiment Report

Deep Learning Model Experiments

University deep learning work comparing image-classification CNNs on CIFAR-10 and recurrent sentiment models on IMDb reviews.

Completed PyTorch CNN RNN / LSTM

Overview

Two experiments, one goal: understand model behaviour.

The folder contains two university deep learning assignments. The first used PyTorch to compare softmax regression and CNN models on CIFAR-10 image classification. The second compared Vanilla RNN, LSTM, and Bidirectional LSTM models for IMDb sentiment analysis.

I am not publishing the full reports or notebooks directly. This page summarises the work and includes only selected chart images that are safe to show publicly.

Tools and concepts

Python and PyTorch for model building, training, and evaluation.
Torchvision transforms and DataLoader workflows for CIFAR-10.
Softmax regression, CNN depth experiments, dropout, weight decay, learning-rate analysis, and mini-batch-size comparison.
IMDb text preprocessing with tokenisation, vocabulary limits, padding, packed sequences, and recurrent models.
Vanilla RNN, LSTM, and Bidirectional LSTM comparison using accuracy, parameter count, and epoch time.

Selected evidence

CNN baseline compared with improved 80 epoch result and loss curves. — CNN baseline compared with an improved longer training run.

Mini-batch size study showing test accuracy over epoch and time. — Mini-batch size study comparing accuracy over epoch and training time.

What I did

I built training and evaluation pipelines, defined model classes, compared model variants, plotted training curves, and wrote up the results in terms of accuracy, generalisation, optimisation behaviour, and training cost.

Key implementation and analysis details

Implemented reusable PyTorch training and evaluation functions for image classification experiments.
Compared CNN depth and regularisation choices to understand how architecture and training settings changed results.
Used packed sequences in the sentiment project so recurrent models could ignore padding tokens.
Compared recurrent model tradeoffs: Vanilla RNN was fastest but weakest, LSTM improved accuracy, and Bidirectional LSTM reached the strongest result.
Reported final sentiment model test accuracy from the source report: Vanilla RNN 59.04%, LSTM 83.49%, Bidirectional LSTM 86.98%.

Problems solved and challenges

The image-classification work required fair comparisons across model variants, which meant keeping the training pipeline consistent. The sentiment task required handling variable-length text, noisy review formatting, and the tradeoff between accuracy and training time.

What I learned

Better accuracy is not the only useful result; training cost and model complexity matter too.
Regularisation and training settings can change model behaviour as much as architecture changes.
Sequence models need careful handling of padding and lengths when working with text.
Error analysis is useful because it shows where a model is confident for the wrong reason.

Future improvements

Add a cleaned public notebook with toy-safe examples and no assessment material.
Rewrite the CNN results into a shorter visual report with fewer charts and clearer takeaways.
Add confusion matrices or sample misclassifications where they are safe and useful.
Compare newer transformer-based sentiment models against the recurrent baseline as a follow-up.