Kayongo Johnson Brian
Software Engineer @Inversepay Africa
Kigali, Rwanda
Actions
I'm Kayongo Johnson Brian, the founder of InversePay, where we’re revolutionizing payments in Africa through cutting-edge AI and machine learning solutions. My passion lies in building intelligent systems that solve real-world challenges, from streamlining payments to automating complex processes. When I'm not scaling InversePay, I'm diving into open-source projects, leading Python Rwanda, and developing innovative tech that makes life smarter, faster, and more efficient. Let’s change the world with code!
Links
Area of Expertise
Topics
X-Ray Vision Powered by Transfer Learning: Keras & TensorFlow in Action!
Discover how transfer learning is revolutionizing healthcare diagnostics with TensorFlow and Keras. In this session, we will dive into a real-world use case of detecting pneumonia from chest X-ray images using powerful pre-trained models like VGG16, InceptionV3, and EfficientNetB0. You'll learn how transfer learning accelerates model training, improves performance in medical image classification, and can be adapted for resource-constrained environments. Whether you're building healthcare solutions or exploring advanced deep learning techniques, this session will equip you with the tools and insights to leverage transfer learning in your next project.
Web Performance API Optimization: Unlocking the Power of Performance
In this exciting presentation, developers of all stripes will be taken on a thrilling journey into the world of Django speed optimization. Our target audience consists of Django fans and web application developers, and they will learn a wealth of useful information that can be applied right away to improve their work.
Transfer Learning Turbo: Detecting Pneumonia with Keras, TensorFlow & Style!
Discover how transfer learning is revolutionizing healthcare diagnostics with TensorFlow and Keras. In this session, we will dive into a real-world use case of detecting pneumonia from chest X-ray images using powerful pre-trained models like VGG16, InceptionV3, and EfficientNetB0. You'll learn how transfer learning accelerates model training, improves performance in medical image classification, and can be adapted for resource-constrained environments. Whether you're building healthcare solutions or exploring advanced deep learning techniques, this session will equip you with the tools and insights to leverage transfer learning in your next project.
TensorFlow Transfer: Mastering Fine-Tuning for Image Classification
In this fun and informative session, we’ll dive into the world of Transfer Learning and Fine-Tuning using TensorFlow and Keras! Ever wondered how AI can tell the difference between cats and dogs without starting from scratch? That’s the magic of transfer learning!
We’ll walk you through the process of leveraging a pre-trained network—a model that’s already learned to recognize general features from a large dataset—and fine-tuning it to solve a new problem: classifying images of cats and dogs. By the end of the session, you’ll understand how to take advantage of pre-trained models to save time, resources, and computing power while achieving high accuracy in image classification.
This hands-on tutorial is perfect for developers looking to get started with deep learning or anyone curious about the power of transfer learning. Whether you're working on small-scale projects or complex tasks, this session will show you how to use pre-trained models to get results fast and efficiently.
Key takeaways:
- Learn the fundamentals of transfer learning and how it applies to image classification.
- Fine-tune a pre-trained model to classify images of cats and dogs.
- Explore the practical benefits of transfer learning in saving time and improving model accuracy.
Paint Like Picasso!! Mastering Neural Style Transfer with TensorFlow
Ever dream of blending your photos with the iconic strokes of Van Gogh or the surrealism of Picasso? In this session, we’ll unlock the magic of Neural Style Transfer—a deep learning technique that lets you transform ordinary images into breathtaking works of art, all powered by TensorFlow!
Neural Style Transfer is the ultimate AI artistry tool that takes two images—a content image and a style image—and merges them to create a unique masterpiece. Imagine taking a photo of your favorite city skyline and styling it like a Monet painting. We’ll dive into how convolutional neural networks are used to optimize image content and style, and how you can harness this technique to create visually stunning images that blend the best of both worlds.
In this session, you’ll learn:
- The fundamentals of Neural Style Transfer and how it works behind the scenes.
- How to implement the original style-transfer algorithm and optimize images for artistic effects.
- The difference between traditional neural style transfer and modern approaches like CycleGAN and Fast Style Transfer that make the process lightning fast.
- Hands-on coding with TensorFlow to generate your own artistic masterpieces.
Whether you’re an AI enthusiast, a creative technologist, or simply someone who loves the fusion of art and technology, this talk will inspire you to explore the endless possibilities of neural style transfer.
Bring your imagination—let’s make AI your paintbrush!
Kayongo Johnson Brian
Software Engineer @Inversepay Africa
Kigali, Rwanda
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top