Anđela Todorović's Projects
All Algorithms implemented in Python
Some basic exercises and algorithms of Reinforcement learning, including Feed Forward, Backpropagation, Gradient descent etc.
python client for reactome content, analysis, and human functional protein interactions (FI) services api calls.
Web programming project
Implementation of the ROLAND: Graph Learning Framework for Dynamic Graphs suitable to integrate into River
Official PyTorch Implementation of SAGPool - ICML 2019
Course materials from the University classes of Introduction to Software Engineering
Implementation of some machine learning algorithms in Swift 4.2 in XCode 10 on the Iris dataset
TensorFlow API for .NET languages
Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task. It is a popular approach in deep learning where pre-trained models are used as the starting point on computer vision and natural language processing tasks given the vast compute and time resources required to develop neural network models on these problems and from the huge jumps in skill that they provide on related problems.
The word2vec algorithm finds much more efficient representations by finding vectors that represent the words. These vectors also contain semantic information about the words. Words that show up in similar contexts, such as "black", "white", and "red" will have vectors near each other. There are two architectures for implementing word2vec, CBOW (Continuous Bag-Of-Words) and Skip-gram.
yolov3 with SPP weights pretrained on Open Images dataset along with config files
Trial implementation of the YOLOv3 algorithm in Swift. Still work in progress :)