The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Secrets of a Kaggle Grandmaster with David Odaibo - #354
11 snips
Mar 5, 2020 
David Odaibo, co-founder and CTO of Analytical AI, shares his journey from a PhD student struggling with machine learning to a Kaggle Grandmaster in computer vision. He discusses his innovations in medical imaging, including a novel method to analyze 3D images using CNNs and LSTMs. Odaibo emphasizes the importance of collaboration in data science competitions and reveals effective strategies for enhancing model performance. He also explores unique data augmentation techniques to prevent overfitting, showcasing how creativity can lead to breakthroughs in AI.
AI Snips
Chapters
Transcript
Episode notes
Kaggle's Practical Value
- David Odaibo started his PhD interested in machine learning but unsure of its practical application.
- Kaggle provided a platform to apply his theoretical knowledge, making concepts clearer.
Early Neural Network Attempt
- Odaibo's initial foray into neural networks involved building a facial recognition system in C#.
- This experience, albeit unsuccessful, sparked his interest in machine learning.
U-Net Success
- In his second Kaggle competition, Odaibo successfully applied the U-Net architecture for image segmentation.
- He placed second out of 950 teams, attributing his success to early adoption and custom implementation of the U-Net.