The Hardest Kaggle Challenge

There's a new $20,000 challenge on Kaggle that uses a dataset titled "The Abstraction and Reasoning Corpus". The aim of this episode is to get you up to speed as fast as possible so that you can participate. This challenge is hosted by Francois Chollet, the creator of the popular deep learning library Keras, and there are still 3 months to go. The goal is to create an algorithm that can learn the relationship between input-output pairs of colored tiles. Sounds simple at first, but upon closer inspection, creating an algorithm that's able to do so given such a small dataset requires genuine AI innovation. Deep Learning won't work because it requires big datasets and expensive compute, so even though this challenge is difficult, it's also the most accessible! We'll be learning about the dataset, related paper, and the various techniques that Kagglers have already attempted. Then, we'll learn about Neural Program Synthesis and future directions that could ultimately solve this problem. Enjoy! Subscribe for more educational videos! It means a lot to me. TWITTER: https://bit.ly/2OHYLbB WEBSITE: https://bit.ly/2OoVPQF INSTAGRAM: https://bit.ly/312pLUb FACEBOOK: https://bit.ly/2OqOhx1 Kaggle Challenge: https://ift.tt/2SqHIKK ARC Dataset: https://ift.tt/2oSNQ2o Convolutional Network Kernel: https://ift.tt/32HnqAh Cellular Automata Kernel: https://ift.tt/2HAcYAN Genetic Algorithm Kernel: https://ift.tt/2VnWCDD Really great paper on Neural Program Synthesis: https://ift.tt/2G0hiq9 Intro to Convolutional Networks: https://www.youtube.com/watch?v=FTr3n7uBIuE Intro to Genetic Algorithms: https://www.youtube.com/watch?v=9zfeTw-uFCw Intro to Cellular Automata: https://www.youtube.com/watch?v=DKGodqDs9sA Simple PointerNet example: https://ift.tt/3ap05pM Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams! Signup for my newsletter for exciting updates in the field of AI: https://goo.gl/FZzJ5w Credits: Kaggle & Kagglers Francois Chollet Google Image Search for the image assets And please support me on Patreon: https://ift.tt/2cMCk13