Goto

Collaborating Authors

This high school kid taught himself to be an AI wizard

#artificialintelligence

If you're deep into the world of artificial intelligence, you certainly know Kaggle, the Google Cloud-owned platform where AI coders compete on projects, often with financial rewards for the winning solutions. The platform recently passed 1 million members, a testament to what a hotbed the field of AI is. He's entered 39 competitions over the past year, recently placing second in a contest to develop an algorithm that can detect duplicate ads on the same platform. With his skill, enthusiasm, and cooperative attitude within the community, Mikel is very much the template of a rising star in the Kaggle and greater AI communities. Except for one thing: Mikel is just 16 years old.


This high school kid taught himself to be an AI wizard

Mashable

If you're deep into the world of artificial intelligence, you certainly know Kaggle, the Google-owned platform where AI coders compete on projects, often with financial rewards for the winning solutions. The platform recently passed 1 million members, a testament to what a hotbed the field of AI is. He's entered 39 competitions over the past year, recently placing second in a contest to develop an algorithm that can detect duplicate ads on the same platform. With his skill, enthusiasm, and cooperative attitude within the community, Mikel is very much the template of a rising star in the Kaggle and greater AI communities. Except for one thing: Mikel is just 16 years old.


YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

arXiv.org Artificial Intelligence

Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for segmentation have to depend on pretrained optical flow models, leading to suboptimal solutions for the problem. End-to-end sequential learning to explore spatialtemporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.e., even the largest video segmentation dataset only contains 90 short video clips. To solve this problem, we build a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS). Our dataset contains 4,453 YouTube video clips and 94 object categories. This is by far the largest video object segmentation dataset to our knowledge and has been released at http://youtube-vos.org. We further evaluate several existing state-of-the-art video object segmentation algorithms on this dataset which aims to establish baselines for the development of new algorithms in the future. Keywords: Video object segmentation, Large-scale dataset, Benchmark.


MIT Shares How Machine Learning Models Can Make Sense Of Nonsense & How This Could Be A Problem

#artificialintelligence

Scientists at the Massachusetts Institute of Technology have stumbled upon an interesting problem with machine learning and image classification. This problem, if not solved, could be harmless or could be deadly, depending on what the system is being used for. Simply put, a model could look at an image and make a prediction based on information that we humans can't make sense of, and it could be wrong. Image classification is used in both medical diagnostics and autonomous driving. The aim is to train a neural network to understand an image in a similar way that a human does.


The unreasonable usefulness of deep learning in medical image datasets

#artificialintelligence

Medical data is horrible to work with. In medical imaging, data stores (archives) operate on clinical assumptions. Unfortunately, this means that when you want to extract an image (say a frontal chest x-ray), you will often get a folder full of other images with no easy way to tell them apart. Depending on the manufacturer, you might end up with horizontally or vertically flipped images. They might have inverted pixel values. The question is, when dealing with a huge dataset (say, 50-100k images), how do you find these aberrations without having a doctor look at all of them?