Software development is always evolving. And Software engineers continue to evolve with it. Before DataEng became a thing, we had DBA's and ETL folks. Software Engineers became more involved with the work and created the DataEng field. Before DevOps, we had Operations/Systems Administrators.

UC Berkeley researchers have developed a robotic learning technology that enables robots to imagine the future of their actions so they can figure out how to manipulate objects they have never encountered before. In the future, this technology could help self-driving cars anticipate future events on the road and produce more intelligent robotic assistants in homes, but the initial prototype focuses on learning simple manual skills entirely from autonomous play. Using this technology, called visual foresight, the robots can predict what their cameras will see if they perform a particular sequence of movements. These robotic imaginations are still relatively simple for now – predictions made only several seconds into the future – but they are enough for the robot to figure out how to move objects around on a table without disturbing obstacles. Crucially, the robot can learn to perform these tasks without any help from humans or prior knowledge about physics, its environment or what the objects are.

University of Pennsylvania workshop addresses potential biases in the predictive technique. Stephen Hawking once warned that advances in artificial intelligence might eventually "spell the end of the human race." And yet decision-makers from financial corporations to government agencies have begun to embrace machine learning's enhanced power to predict--a power that commentators say "will transform how we live, work, and think." During the first of a series of seven Optimizing Government workshops held at the University of Pennsylvania Law School last year, Aaron Roth, Associate Professor of Computer and Information Science at the University of Pennsylvania, demystified machine learning, breaking down its functionality, its possibilities and limitations, and its potential for unfair outcomes. Chairman of the Penn Department of Criminology Richard Berk offers commentary. Machine learning, in short, enables users to predict outcomes using past data sets, Roth said.

Jeanne Pepper Bernstein has been searching for her 19-year-old son since he went missing in Lake Forest last Tuesday. On Sunday afternoon, she had a message for him. "If there's any way you can come home, whatever has happened, wherever you've been, whoever you've talked to -- it doesn't matter," she said in an interview with The Times. "We love you so much that we would give up everything we have to have you back." As she offered her wrenching plea, family and friends used drones to canvass the Foothill Ranch area of Lake Forest, where authorities believe Blaze Bernstein was last seen by a friend in Borrego Park.

These are two of the greatest challenges people face when deploying deep learning solutions. Fact is, while highly accurate, deep learning algorithms are complex and require more computation than other approaches. The analysis of massive data sets can lead to high power and heat dissipation in data centers which limits processing speeds; always-on applications can quickly drain power and memory resources in portable devices, such as smartphones and wearables. That limits real-world applications, particularly on mobile and handheld devices. One of the greatest limitations of progress in deep learning is the amount of computation available.

Artificial intelligence (AI) is the perfect example of how something new could be used to change every aspect of our lives when we change the lens. And education is an area that has unlimited potential to utilize innovation. The ability to tap into new technologies to enhance and accelerate the learning process can streamline everything from admissions and grading to student access to vital resources. One of the simplest but impactful things AI can do for the educational space is to speed up the administrative process both for institutions and educators. The tedious process of grading homework, evaluating essays and measuring student responses can require valuable time from lecturers and teachers who would prefer to focus on their lesson planning and one-on-one time with students.

Today, it is no longer a question of adopting AI or not. Instead, ask yourself if you and your sales team are ready for the inevitable. Artificial intelligence for business is a reality. If your goal is to forge ahead and lead in your field, then you need to adapt to a workplace where AI plays a crucial role. As J.J. Kardwell, founder, and CEO of predictive marketing software company EverString put it: "Growth-focused sales organizations of every size and stage cannot afford to ignore the benefits of AI-assisted sales."

The first step is often the hardest to take, and when given too much choice in terms of direction it can often be debilitating. This post aims to take a newcomer from minimal knowledge of machine learning in Python all the way to knowledgeable practitioner in 7 steps, all while using freely available materials and resources along the way. The prime objective of this outline is to help you wade through the numerous free options that are available; there are many, to be sure, but which are the best? What is the best order in which to use selected resources? It would probably be helpful to have some basic understanding of one or both of the first 2 topics, but even that won't be necessary; some extra time spent on the earlier steps should help compensate.

Learning with streaming data has attracted much attention during the past few years. Though most studies consider data stream with fixed features, in real practice the features may be evolvable. For example, features of data gathered by limited-lifespan sensors will change when these sensors are substituted by new ones. In this paper, we propose a novel learning paradigm: \emph{Feature Evolvable Streaming Learning} where old features would vanish and new features would occur. Rather than relying on only the current features, we attempt to recover the vanished features and exploit it to improve performance. Specifically, we learn two models from the recovered features and the current features, respectively. To benefit from the recovered features, we develop two ensemble methods. In the first method, we combine the predictions from two models and theoretically show that with the assistance of old features, the performance on new features can be improved. In the second approach, we dynamically select the best single prediction and establish a better performance guarantee when the best model switches. Experiments on both synthetic and real data validate the effectiveness of our proposal.

The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large datasets. To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. As an additional benefit, Mean Teacher improves test accuracy and enables training with fewer labels than Temporal Ensembling. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels. We also show that a good network architecture is crucial to performance. Combining Mean Teacher and Residual Networks, we improve the state of the art on CIFAR-10 with 4000 labels from 10.55% to 6.28%, and on ImageNet 2012 with 10% of the labels from 35.24% to 9.11%.