Skip to content
View timif2's full-sized avatar

Block or report timif2

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
timif2/README.md

About me

My enthusiasm lies within the realm of Data Science, built upon a solid base of mathematics, economics, and machine learning. At present, I am studying an MSc. in Statistics and have graduated from studying a BSc. in Economics and Mathematics. Personally, I enjoy utilising and leveraging data-driven solutions in order to solve complex problems, and telling stories through data.

View my portfolio here.


Data Science Projects

This page a collection is a collection of my selected data science related projects, used to explore components of machine learning.

At the moment, from a more theoretical perspective, I am interested in the applications of Transformer architecture. As such, a few of my projects are exploring applications them. The versatile and exciting applications in NLP and Computer Vision are what I find interesting. You can find my CV/resume here.

I am currently developing an educational web app on transformers. If you would like to contact me about this please send me an email.

Neural Networks

Sequence classification with LSTM Recurrent Neural Network, using Keras

GitHub

Explored movie review sentiment classification problem using LSTM Recurrent Neural Network, with Keras.

Classification using neural networks in PyTorch

GitHub

Neural network for basic multi - class classification.

Computer Vision

Vision Transformer (ViT) from scratch in PyTorch

GitHub

A paper implementation of the (original) Vision Transformer (ViT) architecture using PyTorch. Applies convolutional neural network (CNN) method. It follows from code by Daniel Bourke

Reports and papers

Modelling Heart Conditions and Train Delays Using Machine Learning Methods

Report and Presentation

Two studies applying Random Forest using R:

  1. Classifying patient heart conditions from ECG data (classification) and 2. Building train delay prediction model (regression). This was joint work with Weiyun Wu, Alastair Harrison and Ying Zhan.

An Exploration into Support Vector Machines (SVMs) with comparisons to other Classification Methods

Report and Presentation

A study on background, performance and evaluation of Support Vector Machines in solving classification problems (in Python), compared with other classification methods. This was a collaboration with Jake Dorman, Anas Almhmadi and Rishabh Agarwal.

Natural Language Processing (NLP)

Text Summarisation, using NLP

GitHub

A project exploring text summarisation, applying tokenisation and extraction method.

Recommendation Systems

Collaborative Filtering system

GitHub

Implementation of a collaborative filtering (CF) based system looking at user - based and item based CF and Alternating Least Squares (ALS) on a restaurant problem.

Paper Implementations

I tend to learn better when trying to apply concepts from papers. Below are some basic paper implementations directly using labml and most of their implementation code:

Generative Adversarial Networks (GANs) implementation using PyTorch

GitHub

Vision Transformer (ViT) implementation

GitHub


Programming skills: Python (Base, Pandas, NumPy, Matplotlib, Scikit-Learn, PySpark, PyTorch), R, SQL, VBA

Machine Learning skills: TensorFlow, SVM, Decision Trees, Random Forest, Gradient Descent, KNN, PCA

If you have any questions or would like to collaborate on a project, don't hesitate to get in touch! Please contact:

Pinned Loading

  1. computer-vision computer-vision Public

    Computer Vision based projects

    Jupyter Notebook

  2. language-models language-models Public

    Projects on language (mainly NLP and LLMs)

    Jupyter Notebook

  3. neural-networks neural-networks Public

    Implementation of Neural Network projects

    Jupyter Notebook

  4. paper-implementations paper-implementations Public

    Implementations of machine learning papers (mainly Transformer based architectures)

    Jupyter Notebook

  5. recommendation-systems recommendation-systems Public

    Projects based on recommendation systems

    Jupyter Notebook

  6. train-delays train-delays Public

    Random Forest model that predicts train delays to Nottingham Station

    R