Google AI Making Decisions on the Fly

Intriguing direction making decisions like we often do,  in a series to address changes in context

Google’s AI enables robots to make decisions on the fly
  By Kyle Wiggers in Venturebeat

In a paper published this week  (technical) on the preprint server Arxiv.org, a team of Google Brain; Google X; and University of Calfornia, Berkeley researchers describe an extension to existing AI methods that enable an agent — for instance, a robot — to decide which action to take while performing a previous action. The idea is that modeling an agent’s behavior after that of a person or an animal will lead to more robust, less failure-prone systems in the future.

The researchers point out that while AI algorithms have achieved success in video games, robotic grasping, and manipulation tasks, most use a blocking observe-think-act paradigm — an agent assumes that its environment will remain static while it “thinks” so that its actions will be executed on the same states from which they were computed. This holds true in simulation but not in the real world, where the environment state evolves as the agent processes observations and plans its next actions. ...."

Malevolence of the Use of Evolving Images

Good-non technical view of the current state of creating and evolving images. Somewhat like the 'photo shopping' enigma still going on, but more subtle and automated.   At first this seems like its not malevolent at all,  just amusing,  but it shows how an AI can be misled, depending how its used by people.

Malevolent Machine Learning   By Chris Edwards in the CACM

Communications of the ACM, December 2019, Vol. 62 No. 12, Pages 13-15
10.1145/3365573

At the start of the decade, deep learning restored the reputation of artificial intelligence (AI) following years stuck in a technological winter. Within a few years of becoming computationally feasible, systems trained on thousands of labeled examples began to exceed the performance of humans on specific tasks. One was able to decode road signs that had been rendered almost completely unreadable by the bleaching action of the sun, for example.

It just as quickly became apparent, however, that the same systems could just as easily be misled.

In 2013, Christian Szegedy and colleagues working at Google Brain found subtle pixel-level changes, imperceptible to a human, that extended across the image would lead to a bright yellow U.S. school bus being classified by a deep neural network (DNN) as an ostrich.

Two years later, Anh Nguyen, then a Ph.D. student at the University of Wyoming, and colleagues developed what they referre3d to as "evolved images." Some were regular patterns with added noise; others looked like the static from an analog TV broadcast. Both were just abstract images to humans, but these evolved images would be classified by DNNs trained on conventional photographs as cheetahs, armadillos, motorcycles, and whatever else the system had been trained to recognize. ... "

Machines Thinking are like Translation

Intriguing idea. Includes video.

A New Approach to Understanding How Machines Think
From Quanta Magazine   Link to full article. 

Been Kim and colleagues at Google Brain developed a system she calls a translator for humans that permits them to ask questions of an artificial intelligence. 

Google Brain research scientist Been Kim is developing a way to ask a machine learning system how much a specific, high-level concept went into its decision-making process.

If a doctor told that you needed surgery, you would want to know why — and you'd expect the explanation to make sense to you, even if you'd never gone to medical school. Been Kim, a research scientist at Google Brain, believes that we should expect nothing less from artificial intelligence. As a specialist in "interpretable" machine learning, she wants to build AI software that can explain itself to anyone.

Since its ascendance roughly a decade ago, the neural-network technology behind artificial intelligence has transformed everything from email to drug discovery with its increasingly powerful ability to learn from and identify patterns in data. But that power has come with an uncanny caveat: The very complexity that lets modern deep-learning networks successfully teach themselves how to drive cars and spot insurance fraud also makes their inner workings nearly impossible to make sense of, even by AI experts. If a neural network is trained to identify patients at risk for conditions like liver cancer and schizophrenia — as a system called "Deep Patient" was in 2015, at Mount Sinai Hospital in New York — there's no way to discern exactly which features in the data the network is paying attention to. That "knowledge" is smeared across many layers of artificial neurons, each with hundreds or thousands of connections.  ... "

Seeking Interpret-ability and Explanation as Components of our Brain

Modeling the apparent structure and resulting operation of the brain is difficult ....   We have lots of neurons gathering data,  and interacting in ways we do not fully understand.   And that results in high level cognitive concepts, like language or consciousness.   This piece looks at these interactions and seeks to produce some interpretive models based on things we know how to model well enough today, interpret and tag visual scenes.  But that is yet a small and simplistic portion of what the Brain does.  What does it mean for deep intelligence?  Like being given a mass of Lego blocks and being asked to model a city without a map.  You can see the engineers starting to sweat.

The Building Blocks of Interpretability

Interpretability techniques are normally studied in isolation.
We explore the powerful interfaces that arise when you combine them — and the rich structure of this combinatorial space. .... 

Researchers from Google and CMU explore ... 

Chris Olah, Google Brain
Arvind Satyanarayan. Google Brain  .... 

With the growing success of neural networks, there is a corresponding need to be able to explain their decisions — including building confidence about how they will behave in the real-world, detecting model bias, and for scientific curiosity. In order to do so, we need to both construct deep abstractions and reify (or instantiate) them in rich interfaces [1] . With a few exceptions [2, 3, 4] , existing work on interpretability fails to do these in concert.

The machine learning community has primarily focused on developing powerful methods, such as feature visualization [5, 6, 7, 8, 9, 10] , attribution [7, 11, 12, 13, 14, 15, 16, 17] , and dimensionality reduction [18] , for reasoning about neural networks. However, these techniques have been studied as isolated threads of research, and the corresponding work of reifying them has been neglected. On the other hand, the human-computer interaction community has begun to explore rich user interfaces for neural networks [19, 20, 21] , but they have not yet engaged deeply with these abstractions. To the extent these abstractions have been used, it has been in fairly standard ways. As a result, we have been left with impoverished interfaces (e.g., saliency maps or correlating abstract neurons) that leave a lot of value on the table. Worse, many interpretability techniques have not been fully actualized into abstractions because there has not been pressure to make them generalizable or composable. .... 

AI Video Recommendations

In the Verge: AI and Video recommendations: 

How YouTube started using Google Brain's AI to improve video recommendations in 2015, which now drive 70% of videos' watch time  —  Google Brain gave YouTube new life  —   .... "