Schedule: Computer Vision sessions

Jason Dai, Yuhao Yang, Jennie Wang, and Guoqiong Song explain how to build and productionize deep learning applications for big data with Analytics Zoo—a unified analytics and AI platform that seamlessly unites Spark, TensorFlow, Keras, and BigDL programs into an integrated pipeline—using real-world use cases from JD.com, MLS Listings, the World Bank, Baosight, and Midea/KUKA. Read more.

Whether you're a scientist wanting to test a problem without building costly real-world rigs, a self-driving car engineer wanting to test AI logic in a virtual world, or a data scientist needing to solve a thorny real-world problem without a production environment, Paris Buttfield-Addison, Tim Nugent, and Mars Geldard teach you how to use solution-driven ML AI problem solving with a game engine. Read more.

PyTorch captured the minds of ML researchers and developers upon its arrival. Now it's matured into a production-ready ML framework with use cases and applications. Mo Patel explores the PyTorch lifecycle via hands-on examples such as image and text classification and linear modeling. You'll cover other aspects of ML such as transfer learning, data modeling, and deploying to production in labs. Read more.

Enhao Gong and Greg Zaharchuk detail AI solutions, cleared by the FDA and powered by industry framework, that deliver 4x–10x faster MRI scans, 4x faster PET scans, and up to 10x dosage reduction. Clinical evaluation at hospitals such as Hoag Hospital, UCSF, and Stanford demonstrates the significant and immediate values of AI to improve the productivity of healthcare workflow. Read more.

Advances in AI and deep learning enable new technologies to mimic how the human brain interprets scenes, objects, and images, which has major implications for businesses that need to extract meaning from overwhelming quantities of unstructured data. Josh Weisberg walks you through how implementing computer vision based in deep neural networks allows machines to see images in an entirely new way. Read more.

Every NLP-based document-processing solution depends on converting documents or images to machine-readable text using an optical character recognition (OCR) solution, but accuracy is limited by the quality of the images. Nagendra Shishodia, Solmaz Torabi, and Chaithanya Manda examine how GANs can bring significant efficiencies by enhancing resolution and denoising scanned images. Read more.

Document understanding is a company-wide initiative at Intuit that aims to make data preparation and entry obsolete through the application of computer vision and machine learning. A team of data scientists, Joy Rimchala, TJ Torres, Xiao Xiao, and Hui Wang, detail the design and modeling methodologies used to build this platform as a service. Read more.

There aren't many systems in the world that need to run hundreds of computer vision models (from classification to segmentation) on billions of visual entities (images, videos, 3-D) daily. Roshan Sumbaly walks you through the challenges faced while building such a platform and how, surprisingly, a lot of the answers were found in traditional software engineering best practices. Read more.

Photographic defects such as noise, exposure, and blur can ruin the perfect shot. Adobe has developed a solution based on GAN that can identify the defective region in images and fix it. Akhilesh Kumar explores how this solution, which can also be applied to fix videos, is better than traditional algorithms and means you won't have to spend hours manually editing the images. Read more.

Tremendous progress has been made in applying machine learning to autonomous driving. Li Erran Li explores recent advances in applying machine learning to solving the perception, prediction, planning, and control problems of autonomous driving as well as some key research challenges. Read more.

Much business data still exists as challenging scanned or snapped documents. Stacy Ashworth and Alberto Andreotti explore a real-world case of reading, understanding, classifying, and acting on facts extracted from such image files using state-of-the-art, open source, deep learning-based optical character recognition (OCR), natural language processing (NLP), and forecasting libraries at scale. Read more.

Over the last few years, convolutional neural networks (CNNs) have risen in popularity, especially in the area of computer vision. However, CNNs are by nature computationally and memory intensive, making them challenging to deploy on a mobile device. Siddha Ganju and Meher Kasam examine optimizing deep neural nets to run efficiently on mobile devices. Read more.

With the fundamental breakthroughs in artificial intelligence and the significant increase of digital health data, there's been enormous interest in AI for healthcare applications. Maithra Raghu examines how to more effectively develop AI algorithms for these settings and the novel prediction challenges and successes arising from the interaction of AI algorithms and human experts. Read more.

Leslie De Jesus examines a machine learning solution enabling the Puerto Rico Science, Technology & Research Trust to identify and classify mosquitoes that may be carrying diseases such as Zika and dengue fever. She outlines the challenges, strategy, and technologies used, the results achieved to date, and the implications of the AI project in helping to address a global threat. Read more.

Join Lindsay Hiebert and Vikrant Viniak as they explore challenges for developers as they design a product that solves a real-world problem using the power of AI and IoT. To unlock the potential of AI at the edge, Intel launched its Intel AI: In Production ecosystem to accelerate prototype to production at the edge with Intel and partner offerings. Read more.

Lately, 360-degree images have become ubiquitous in industries from real estate to travel. They enable an immersive experience that benefits consumers but creates a challenge for businesses to direct viewers to the most important parts of the scene. Shourabh Rawat walks you through how to identify and extract engaging static 2-D images using specific algorithms and deep learning methods. Read more.

Whether you're a scientist wanting to test a problem without building costly real-world rigs, a self-driving car engineer wanting to test AI logic in a constrained virtual world, or a data scientist needing to solve a thorny real-world problem without a production environment, Paris Buttfield-Addison, Mars Geldard, and Tim Nugent teach you how to use AI problem-solving using game engines. Read more.