I worked with 3 other students on implementing a Generative Adversarial Network. GANs is a type of neural network architecture used for generating instances of training data. For instances, when images are fed into GANs, an algorithm can create or generate similar images never seen before. This technique is used in DeepFakes. It is a very ethically sensitive technology, and we considered all of it.
As a demonstration, we compared two types of GANs viz Fully Connected(FC) and Deep Convolutional(DC) GANs on 4 datasets, MNIST, FASHION-MNIST, CIFAR10 and CIFAR100, using the Frechet Inception Distance score.
The results are outstanding. More details of this can be found in the poster below.
The source code can be found here https://github.com/Chuukwudi/FC-GAN-vs-DC-GAN-comparison-on-MNIST-MNIST_Fashion-Cifar10-and-Cifar100-Datasets and can be directly run on google colab.
I am a masters student of Applied Artificial Intelligence, with a bachelors degree in Electronic and Computer Engineering. I am passionate about using Artificial Intelligence to solve problems, especially in Healthcare, Business, Technology and Education.
Presently, a Graduate Research volunteer (Cancer and Game Theory) and a student worker, Teesside University Digital Skills for Growth. I assist my lecturers in delivering a course in Machine Learning to grow and improve businesses and companies (Funded by the European Union Social Fund).
Skills/Proficiencies:
Programming: Python, R, C++, Matlab, Power Query, DAX
Machine Learning: Scikit-learn, NLTK, SciPy, NumPy.
Deep Learning: TensorFlow, Keras, Pytorch
Data Visualisation: Pandas, Matplotlib, Seaborn, Plotly, GGPlot2
Business Intelligence: Microsoft Power BI
Languages: English(C1, IELTS 7.0), German(B1, Von Goethe Institut)
General: Conflict Management, Communication and Leadership.
Others: LATEX, Microsoft Office Suite.
I love learning new things; I am tech-savvy and play the piano in my free time.
