Author: Mariya Yao

14 Design Patterns To Improve Your Convolutional Neural Networks

Ever since deep convolutional neural networks (CNNs) outperformed humans in image classification tasks in 2011, they have been the industry go-to standard for tasks in computer vision like image segmentation, object detection, scene labeling, tracking, text detection, and more. Unfortunately, the art of training neural networks is not easy to master. As with previous machine learning methods, the devil is in the details, but there are so many more details to manage. What are the limitations of your data and your hardware? Should you start with AlexNet, VGG, GoogLeNet (Inception), or ResNet? There’s even a ResNet in ResNet option. How many dense...

Read More

4 Approaches To Natural Language Processing & Understanding

In 1971, Terry Winograd wrote the SHRDLU program while completing his PhD at MIT. SHRDLU features a world of toy blocks where the computer translates human commands into physical actions, such as “move the red pyramid next to the blue cube.” To succeed in such tasks, the computer must build up semantic knowledge iteratively, a process Winograd discovered was brittle and limited.   The rise of chatbots and voice activated technologies has renewed fervor in natural language processing (NLP) and natural language understanding (NLU) techniques that can produce satisfying human-computer dialogs. Unfortunately, academic breakthroughs have not yet translated to...

Read More

How Tech Giants Use Economy Of Scale To Power A.I. For Good

“90% of the world’s supercomputers run on Intel technology,” Diane Bryant tells me at SxSW. “And 95% of artificial intelligence solutions run on Intel Xeon and Xeon Phi processors.” Bryant is an Intel veteran who joined the semiconductor giant right after getting an electrical engineering degree from U.C. Davis. Starting a a microprocessor design engineer, she quickly worked her way up the ranks, spending 4 years as Intel’s CIO before moving on to lead their Data Center Group. With recent acquisitions of Nervana and Mobileye, Intel is building a solid position in the A.I. wars. Every major tech company...

Read More

5 Secrets Your Tweets Reveal About You

Big data firms like Cambridge Analytica made headlines when they claimed to sway Election 2016 results by deducing personality traits from social media profiles and third-party data firms and serving highly manipulative ads to sway public opinion. Leveraging a trove of data points – such as your shopping habits, magazine subscriptions, Facebook likes, and up to 5000 other inputs – Analytica built predictive personality models for 220 million adults in the U.S. These highly detailed dossiers enabled Analytica to do “behavioral microtargeting” based on your personality. They are hardly the only ones who do so. Fortune 500 brand marketers,...

Read More

Understanding The Limits Of Deep Learning

Artificial intelligence has reached peak hype. News outlets report that companies have replaced workers with IBM Watson and algorithms are beating doctors at diagnoses. New A.I. startups pop up every day and claim to solve all your personal and business problems with machine learning. Ordinary objects like juicers and wifi routers suddenly advertise themselves as “powered by AI”. Not only can smart standing desks remember your height settings, they can also order you lunch. Much of the A.I. hubbub is generated by reporters who’ve never trained a neural network and startups  hoping to be acquihired for engineering talent despite not solving any real business problems....

Read More