Andrew Ng is most of the world's most prominent AI scientist's and educators. On this episode of CxOTalk, he shares practical advice for adopting AI in the enterprise. Dr. Andrew Ng is a globally recognized leader in AI (Artificial Intelligence). He has helped two of the world's leading technology companies in their "AI transformation": He was Chief Scientist at Baidu, where he led the company's 1300 person AI Group and was responsible for driving the company's global AI strategy and infrastructure. He was also the founding lead of the Google Brain team.

About a year ago, I wrote that mounting AI hype would likely give way to yet another AI winter. Now, according to the panelists at "the world's leading academic AI conference" the temperature is already falling. Most recent advances in AI have come through a pair of related technologies: Deep Learning and Neural Networks. The ideas beneath these, however, are more than 70 years old. Warren McCulloch and Walter Pitts (1943) opened the subject by creating a computational model for neural networks…The first functional networks with many layers were published by Ivakhnenko and Lapa in 1965, as the Group Method of Data Handling.

Look in the wrong place, and you'll get the wrong answers. Five years ago, Elon Musk said "With Artificial Intelligence (AI) we are summoning the demon". A report by the Brookings Institution's AI and Emerging Tech Initiative notes that fearful warnings about new technology like this are nothing new. When C. Babbage created the first "computer" in the mid-19th century: "The idea that God-given human reason could be replaced by a machine was fearfully received by Victorian England in a manner similar to today's concern about machines being able to think like humans." However, while Musk called for (preventive) "[r]egulatory oversight… just to make sure that we don't do something foolish", the report warns that regulation of AI would be meaningful only if it "focused on the tangible effects of the technology."

Sitting at the nexus of data science, computer vision, and machine learning, artificial intelligence (AI) has the promise to provide insights from large, high-dimensional datasets that can stay otherwise hidden from traditional data analysis approaches. However, its application in materials science has been comparatively slower than some fields due to the specialized knowledge required to apply AI to physical systems, as well as the wide variety of problems and data types encountered. In an effort to push forward the state-of-the-art in materials science research, Carnegie Mellon University (CMU) and the Air Force Research Laboratory (AFRL) are establishing a collaborative Center of Excellence. The center will leverage the strengths of the two institutions to develop next-generation aerospace materials, establish a pipeline of research talent with both AI and materials science expertise, and advance the materials science field by integrating AI into materials research and design. The 5-year, $7.5M joint Center of Excellence, named Data-Driven Discovery Of Optimized Multifunctional Material Systems (D3OM2S), is supported by an award from the Air Force Office of Scientific Research (AFOSR) and the AFRL Materials and Manufacturing Directorate.

I will also discuss the common technical challenges of executing A/B tests on ML algorithms, such as infrastructure requirements, connecting online and offline metrics, and handling ramp up periods for online learning algorithms. Overall, the goal of this talk will be to motivate ML practitioners to use A/B testing when evaluating their algorithms and provide them with high-level guidelines on how to do it. Profile Pavel Dmitriev is a Vice President of Data Science at Outreach, where he works on enabling data driven decision making in sales through experimentation and machine learning. He was previously a Principal Data Scientist with Microsoft's Analysis and Experimentation team, where he worked on scaling experimentation in Bing, Skype, and Windows OS. Pavel co-authored numerous papers at top-tier data mining and machine learning conferences, such as WWW, ICSE, KDD, has given keynotes and tutorials at WWW, SIGIR, SEAA, and KDD.

SPRINGFIELD, MASSACHUSETTS – Police departments around the U.S. are asking citizens to trust them to use facial recognition software as another handy tool in their crime-fighting toolbox. But some lawmakers -- and even some technology giants -- are hitting the brakes. Are fears of an all-seeing, artificially intelligent security apparatus overblown? Not if you look at China, where advancements in computer vision applied to vast networks of street cameras have enabled authorities to track members of ethnic minority groups for signs of subversive behavior. American police officials and their video surveillance industry partners contend that won't happen here.

Toyota Motor Corp. plans to first deploy advanced self-driving features in commercial vehicles before adding them to cars meant for personal use, a senior official at the Japanese auto major said on Tuesday. It will be easier to apply self-driving technology that does not require constant and direct human-monitoring to taxis and vehicles Toyota is developing, including on-demand ride services, mobile shops and ambulatory hospitals, said James Kuffner, chief of Toyota Research Institute-Advanced Development (TRI-AD). The operators of these vehicles could control when and where they are deployed and oversee their maintenance, he told reporters at the opening of its new offices in Tokyo. "It will take more time to achieve'Level 4' for a personally-owned vehicle," Kuffner said, referring to the automation level at which vehicles can drive themselves under limited conditions. "Level 4 is really what we're striving for to first appear in mobility as a service," he added.

The simultaneous control of multiple coordinated robotic agents represents an elaborate problem. If solved, however, the interaction between the agents can lead to solutions to sophisticated problems. The concept of swarming, inspired by nature, can be described as the emergence of complex system-level behaviors from the interactions of relatively elementary agents. Due to the effectiveness of solutions found in nature, bio-inspired swarming-based control techniques are receiving a lot of attention in robotics. One method, known as swarm shepherding, is founded on the sheep herding behavior exhibited by sheepdogs, where a swarm of relatively simple agents are governed by a shepherd (or shepherds) which is responsible for high-level guidance and planning. Many studies have been conducted on shepherding as a control technique, ranging from the replication of sheep herding via simulation, to the control of uninhabited vehicles and robots for a variety of applications. We present a comprehensive review of the literature on swarm shepherding to reveal the advantages and potential of the approach to be applied to a plethora of robotic systems in the future.

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis.

Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can efficiently satisfy the constraints of different devices. In contrast, existing methods often rely on heuristic and manual adjustments to maintain accuracy, support only coarse compression policies, or target specific device constraints that limit their applicability. We address these limitations by proposing the TOlerance-based COmpression (TOCO) framework. TOCO uses an in-depth analysis of the model, to maintain the accuracy, in an active learning system. The results of the analysis are tolerances that can be used to perform compression in a fine-grained manner. Finally, by decoupling compression from the tolerance analysis, TOCO allows flexibility to changes in the hardware.