This repo outlines a proposed neural network model for generation of image descriptors for image representation in the Euclidean Space. With these descriptors, matching, verification and retrieval tasks should be performed successfully. In the introduced project, we were given a baseline approach for the creation of image descriptors and were asked perform a series of improvements besed. Our approach should be outlined in a 4-page (paper-style) report and be accompanied by a notebook with our code written in Keras and Python.
This repo outlines my submission for the coursework of the course "EE3-25 - Deep Learning" at Imperial College London during the academic year 2018-2019. It contains both the paper-report and the jupyter notebook with the Python / Keras code.
"This is a continuation of the Autumn term course EE3-35 Machine Learning. In contrast to machine learning included in EE3-23, EE3-25 Deep Learning will focus on deep neural network based learning. It introduces the background and illustrates how deep learning is impacting our understanding of intelligence and contributing to the practical design of intelligent machines. Deep learning is currently the most active area of research and development and in high demand for experts by hi-tech start-ups, large companies as well as academia. It is the preferred approach for modern AI and machine learning in any domain. Deep learning techniques enable us to automatically extract features from data so as to solve predictive tasks, such as speech recognition, object recognition, machine translation, question-answering, anomaly detection, medical diagnosis and prognosis, automatic algorithm configuration, personalisation, robot control, time series forecasting, and much more." [EE3-25-Deep Learning-Imperial College London]
This repo contains mainly Jupyter notebook which can be run after installing Jupyter Notebook. Run the following command at the Terminal (Mac/Linux) or Command Prompt (Windows):
pip install notebook