Whether you get your news from Facebook or from the Wall Street Journal you can’t help having heard that China is out to displace the US as the world leader in AI. Variously you may have heard that it’s already happened or soon inevitably will.
The twin questions of when they will succeed (is it inevitable) or whether they will succeed (if ever) is one I get all the time. As a red-white-and-blue American I hope not. As a world citizen of the tribe of data scientists I wonder why we can’t just all get along. And as those divided feelings should presage, the current state of this struggle is about both competition and cooperation, and also about unintended consequences. Read More
Daily Archives: July 30, 2020
Competing in Artificial Intelligence Chips: China’s Challenge amid Technology War
This special report assesses the challenges that China is facing in developing its artificial intelligence (AI) industry due to unprecedented US technology export restrictions. A central proposition is that China’s achievements in AI lack a robust foundation in leading-edge AI chips, and thus the country is vulnerable to externally imposed supply disruptions. Success in AI requires mastery of data, algorithms and computing power, which, in turn, is determined by the performance of AI chips. Increasing computing power that is cost-effective and energy-saving is the indispensable third component of this magic AI triangle.
Drawing on field research conducted in 2019, this report contributes to the literature by addressing China’s arguably most immediate and difficult AI challenges. Read More
An AI Learned To See Through Obstructions!
A new neural network could help computers code themselves
Computer programming has never been easy. The first coders wrote programs out by hand, scrawling symbols onto graph paper before converting them into large stacks of punched cards that could be processed by the computer. One mark out of place and the whole thing might have to be redone.
Nowadays coders use an array of powerful tools that automate much of the job, from catching errors as you type to testing the code before it’s deployed. But in other ways, little has changed. That’s why some people think we should just get machines to program themselves.
Justin Gottschlich, director of the machine programming research group at Intel, and his colleagues call this machine programming. Read More
Neuroevolution of Self-Interpretable Agents
Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain focused on important parts of our world without distraction from irrelevant details. Motivated by selective attention, we study the properties of artificial agents that perceive the world through the lens of a self-attention bottleneck. By constraining access to only a small fraction of the visual input, we show that their policies are directly interpretable in pixel space. We find neuroevolution ideal for training self-attention architectures for vision-based reinforcement learning (RL) tasks,allowing us to incorporate modules that can include discrete, non-differentiable operations which are useful for our agent. We argue that self-attention has similar properties as indirect encoding, in the sense that large implicit weight matrices are generated from a small number of key-query parameters, thus enabling our agent to solve challenging vision based tasks with at least 1000x fewer parameters than existing methods. Since our agent attends to only task critical visual hints, they are able to generalize to environments where task irrelevant elements are modified while conventional methods fail. Read More
#image-recognition, #reinforcement-learning, #visionNIST Launches Investigation of Face Masks’ Effect on Face Recognition Software
Algorithms created before the pandemic generally perform less accurately with digitally masked faces.
Now that so many of us are covering our faces to help reduce the spread of COVID-19, how well do face recognition algorithms identify people wearing masks? The answer, according to a preliminary study by the National Institute of Standards and Technology (NIST), is with great difficulty. Even the best of the 89 commercial facial recognition algorithms tested had error rates between 5% and 50% in matching digitally applied face masks with photos of the same person without a mask.
The results were published today as a NIST Interagency Report (NISTIR 8311), the first in a planned series from NIST’s Face Recognition Vendor Test (FRVT) program on the performance of face recognition algorithms on faces partially covered by protective masks. Read More
Rick's Cafe AI 