The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely autonomous deep learning (ADL), is proposed in this paper. Unlike traditional deep learning methods, ADL features a flexible structure where its network structure can be constructed from scratch with the absence of initial network structure via the self-constructing network structure. ADL specifically addresses catastrophic forgetting by having a different-depth structure which is capable of achieving a trade-off between plasticity and stability. Network significance (NS) formula is proposed to drive the hidden nodes growing and pruning mechanism. Drift detection scenario (DDS) is put forward to signal distributional changes in data streams which induce the creation of a new hidden layer. Maximum information compression index (MICI) method plays an important role as a complexity reduction module eliminating redundant layers. The efficacy of ADL is numerically validated under the prequential test-then-train procedure in lifelong environments using nine popular data stream problems. The numerical results demonstrate that ADL consistently outperforms recent continual learning methods while characterizing the automatic construction of network structures.

Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many real applications, it is often desirable to have the flexibility of learning additional concepts, without re-training on the full training set. This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes; and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the overall performance of both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes. In each episode, we train a set of new weights to recognize novel classes until they converge, and we show that the technique of recurrent back-propagation can back-propagate through the optimization process and facilitate the learning of the attractor network regularizer. We demonstrate that the learned attractor network can recognize novel classes while remembering old classes without the need to review the original training set, outperforming baselines that do not rely on an iterative optimization process.

Representation learning is typically applied to only one mode of a data matrix, either its rows or columns. Yet in many applications, there is an underlying geometry to both the rows and the columns. We propose utilizing this coupled structure to perform co-manifold learning: uncovering the underlying geometry of both the rows and the columns of a given matrix, where we focus on a missing data setting. Our unsupervised approach consists of three components. We first solve a family of optimization problems to estimate a complete matrix at multiple scales of smoothness. We then use this collection of smooth matrix estimates to compute pairwise distances on the rows and columns based on a new multi-scale metric that implicitly introduces a coupling between the rows and the columns. Finally, we construct row and column representations from these multi-scale metrics. We demonstrate that our approach outperforms competing methods in both data visualization and clustering.

Flying cars, augmented reality glasses and contact lenses that can detect diabetes: They're all innovations born out of Google X, the skunkworks division of Alphabet. Three years ago Spanish telco giant Telefónica established Alpha, a lab in Barcelona staffed by around 100 people, working in stealth on innovative technology that holds the promise of a potential new revenue streams. The person running all things AI at the lab is Pascal Weinberger, 21. Weinberger is originally from Germany and like many other computer programmers is self-taught. He dropped out of a bachelor's degree, having "enrolled to keep my parents happy," but by 15 had already taken several remote courses in programming at MIT.

What are the best sources to study machine learning and artificial intelligence? You're in luck - now is better than ever before to start studying machine learning and artificial intelligence. The field has evolved rapidly and grown tremendously in recent years. Experts have released and polished high quality open source software tools and libraries. New online courses and blog posts emerge every day.

New school: The new college of computing is being built with $350 million in funding from Stephen A. Schwarzman, the CEO and cofounder of Blackstone, a private equity firm. Schwarzman has already donated billions to other institutions for studying issues related to AI. MIT's new Stephen A. Schwarzman College of Computing will create 50 new faculty positions and numerous fellowships for graduate students. The school will open next September and will be housed in existing buildings at MIT before moving to its own space, expected in 2022.

The Massachusetts Institute of Technology is pumping $1 billion into a new center for the study of the "global opportunities and challenges presented by the prevalence of computing and the rise of artificial intelligence," the school said Monday. In a statement, MIT said the MIT Stephen A. Schwarzman College of Computing will open in September 2019 as "an interdisciplinary hub for work in computer science, AI, data science, and related fields." A $350 million foundational gift from Schwarzman, head of the massive investment firm Blackstone, will get the project rolling. In addition to Schwarzman's gift, MIT has raised another $300 million for the college that bears his name, with further fundraising being "actively pursued" to raise the $1 billion needed for the learning hub, the statement said. "The College's attention to ethics matters enormously to me, because we will never realize the full potential of these advancements unless they are guided by a shared understanding of their moral implications for society," Schwarzman said in the release.

MIT announced today that it is massively doubling down on the future of computer science with the launch of a new college of computing. The university is committing $1 billion in resources to the new school, and the university received a $350 million donation from Stephen A. Schwarzman, who will be the naming donor. MIT said that its commitment is the largest of a university yet to the discipline. The university is already one of the leaders in computer science, with a famed department located in the School of Engineering. The new initiative will see computer science, artificial intelligence, and data science placed in the new school, complete with a new dean and around 50 new faculty positions according to the university.

Ever since the packet switching network known as ARPANET was demilitarized and turned over to academic researchers in the late 1970s, the fields of Information Technology and education have crossed paths and formed partnerships for the benefit and improvement of society. The activities we know as eLearning and online education today will become the standards of academic instruction tomorrow, and the manner courses are delivered will be determined by Artificial Intelligence. The technological advances listed above have unfolded over four decades; academic researchers believe that the next wave of tech progress in education will involve machine learning and other fields of AI development. The first ripples of this wave are already here, and they involve algorithms and natural language processing. Botsify, for example, is a smart chatbot platform designed specifically for the education sector, but this is only the beginning.

SAN FRANCISCO (Reuters) - Dozens of employers looking to hire the next generation of tech employees descended on the University of California, Berkeley in September to meet students at an electrical engineering and computer science career fair. Boris Yue, 20, was one of thousands of student attendees, threading his way among fellow job-seekers to meet recruiters. But Yue wasn't worried about so much potential competition. While the job outlook for those with computer skills is generally good, Yue is in an even more rarified category: he is studying artificial intelligence, working on technology that teaches machines to learn and think in ways that mimic human cognition. His choice of specialty makes it unlikely he will have difficulty finding work.