Hi, my name is Timi! My interests lie in the intersection of AI and Data Science and I love building applications (e.g. ways to build robust RAG architectures) and exploring ways to utilise the latest advancements in the field in a practical way. Academically, I completed my MSc. in Statistics, where I wrote my thesis on the adversarial robustness of Spiking Neural Networks, intersecting AI Safety and neural networks.
View my portfolio here.
Explored movie review sentiment classification problem using LSTM Recurrent Neural Network, with Keras.
Neural network for basic multi - class classification.
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
Technical report studying the resistance to adversarial attack of rate - encoded SNNs, across various white and black box attacks.
Report and Presentation
Two studies applying Random Forest using R: 1. Classifying patient heart conditions from ECG data (classification); 2. Building train delay prediction model (regression). This was joint work with Weiyun Wu, Alastair Harrison and Ying Zhan.
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.
A project exploring text summarisation, applying tokenisation and extraction method.
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.
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:
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:
- Email: timicsbe@gmail.com
- LinkedIn: linkedin.com/in/timifolaranmi/