I have a first class honors masters degree in Digital Electronics from the University of Sheffield.
I’m currently doing a PhD at the Heriot-Watt University on applying natural language processing based machine learning algorithms to programming languages.
My research interests also include reinforcement learning and attention mechanisms.
I enjoy reading, listening to podcasts and playing board games. I’m also trying to learn German, but it’s not going very well.
You can contact me on twitter or via e-mail.
- easynlp: A library for performing natural language processing - such as zero-shot classification, translation, named entity recognition, summarization, and question answering - inference on given data utilizing the pre-trained models from transformers.
- pytorch-sentiment-analysis: A tutorial on how to implement some common deep learning based sentiment analysis (text classification) models in PyTorch with torchtext, specifically the NBOW, GRU, bi-LSTM, CNN and Transformer models. Somehow got popular and has quite a few stars.
- pytorch-seq2seq: A tutorial implementing neural (deep learning based) sequence-to-sequence models in PyTorch with torchtext, by implementing six NMT papers. Also has quite a few stars and was used as a basis for the official PyTorch language translation tutorial.
- pytorch-image-classification: A tutorial covering how to implement some deep learning computer vision models in PyTorch with torchvision. Covers: a basic multi-layer perceptron, LeNet, AlexNet, VGG and ResNet.
- a-tour-of-optimizers: A tutorial on common optimization algorithms used for neural networks, including: SGD, Adagrad, Adadelta, RMSprop and Adam.
- notes: My personal Zettelkasten notes in Markdown. The notes are created with obsidian but should be compatible with any Markdown rendering tool.
One of my 2021 resolutions is to write more. Most of the writing will be about machine learning, programming and tech.
Around once a week I round up all of the interesting articles I’ve seen online and post them alongside my comments and adjacent thoughts.
Posts that don’t fit into the above section.