Radiant Earth Foundation has released "LandCoverNet," a human-labelled global land cover classification training dataset. This release contains data across Africa, which accounts for 1/5 of the global dataset. Available for download on Radiant MLHub, the open geospatial library, LandCoverNet will enable accurate and regular land cover mapping for timely insights into natural and anthropogenic impacts on the Earth. Global land cover maps derived from Earth observations are not new, but the influx of open-access high spatial resolution Earth observations, such as that from the European Space Agency's Sentinel missions, coupled with improved computer power, encouraged the development of advanced algorithms. Machine learning models applied to high resolution remotely sensed imagery can classify land cover classes more accurately and faster, given the availability of high-quality training data.

One fundamental goal of high-dimensional statistics is to detect or recover structure from noisy data. In many cases, the data can be faithfully modeled by a planted structure (such as a low-rank matrix) perturbed by random noise. But even for these simple models, the computational complexity of estimation is sometimes poorly understood. A growing body of work studies low-degree polynomials as a proxy for computational complexity: it has been demonstrated in various settings that low-degree polynomials of the data can match the statistical performance of the best known polynomial-time algorithms for detection. While prior work has studied the power of low-degree polynomials for the task of detecting the presence of hidden structures, it has failed to address the estimation problem in settings where detection is qualitatively easier than estimation. In this work, we extend the method of low-degree polynomials to address problems of estimation and recovery. For a large class of "signal plus noise" problems, we give a user-friendly lower bound for the best possible mean squared error achievable by any degree-D polynomial. To our knowledge, this is the first instance in which the low-degree polynomial method can establish low-degree hardness of recovery problems where the associated detection problem is easy. As applications, we give a tight characterization of the low-degree minimum mean squared error for the planted submatrix and planted dense subgraph problems, resolving (in the low-degree framework) open problems about the computational complexity of recovery in both cases.

Tensor, also known as multi-dimensional array, arises from many applications in signal processing, manufacturing processes, healthcare, among others. As one of the most popular methods in tensor literature, Robust tensor principal component analysis (RTPCA) is a very effective tool to extract the low rank and sparse components in tensors. In this paper, a new method to analyze RTPCA is proposed based on the recently developed tensor-tensor product and tensor singular value decomposition (t-SVD). Specifically, it aims to solve a convex optimization problem whose objective function is a weighted combination of the tensor nuclear norm and the l1-norm. In most of literature of RTPCA, the exact recovery is built on the tensor incoherence conditions and the assumption of a uniform model on the sparse support. Unlike this conventional way, in this paper, without any assumption of randomness, the exact recovery can be achieved in a completely deterministic fashion by characterizing the tensor rank-sparsity incoherence, which is an uncertainty principle between the low-rank tensor spaces and the pattern of sparse tensor.

The proposed article aims at offering a comprehensive tutorial for the computational aspects of structured matrix and tensor factorization. Unlike existing tutorials that mainly focus on {\it algorithmic procedures} for a small set of problems, e.g., nonnegativity or sparsity-constrained factorization, we take a {\it top-down} approach: we start with general optimization theory (e.g., inexact and accelerated block coordinate descent, stochastic optimization, and Gauss-Newton methods) that covers a wide range of factorization problems with diverse constraints and regularization terms of engineering interest. Then, we go `under the hood' to showcase specific algorithm design under these introduced principles. We pay a particular attention to recent algorithmic developments in structured tensor and matrix factorization (e.g., random sketching and adaptive step size based stochastic optimization and structure-exploiting second-order algorithms), which are the state of the art---yet much less touched upon in the literature compared to {\it block coordinate descent} (BCD)-based methods. We expect that the article to have an educational values in the field of structured factorization and hope to stimulate more research in this important and exciting direction.

In this paper, we develop novel perturbation bounds for the high-order orthogonal iteration (HOOI) [DLDMV00b]. Under mild regularity conditions, we establish blockwise tensor perturbation bounds for HOOI with guarantees for both tensor reconstruction in Hilbert-Schmidt norm $\|\widehat{\bcT} - \bcT \|_{\tHS}$ and mode-$k$ singular subspace estimation in Schatten-$q$ norm $\| \sin \Theta (\widehat{\U}_k, \U_k) \|_q$ for any $q \geq 1$. We show the upper bounds of mode-$k$ singular subspace estimation are unilateral and converge linearly to a quantity characterized by blockwise errors of the perturbation and signal strength. For the tensor reconstruction error bound, we express the bound through a simple quantity $\xi$, which depends only on perturbation and the multilinear rank of the underlying signal. Rate matching deterministic lower bound for tensor reconstruction, which demonstrates the optimality of HOOI, is also provided. Furthermore, we prove that one-step HOOI (i.e., HOOI with only a single iteration) is also optimal in terms of tensor reconstruction and can be used to lower the computational cost. The perturbation results are also extended to the case that only partial modes of $\bcT$ have low-rank structure. We support our theoretical results by extensive numerical studies. Finally, we apply the novel perturbation bounds of HOOI on two applications, tensor denoising and tensor co-clustering, from machine learning and statistics, which demonstrates the superiority of the new perturbation results.

Artificial intelligence is already impacting our lives. And the use of AI for social functioning is on an all-time high. Be it getting riding directions through our smartphone or getting daily reminders by using our health system to extend our workouts; all these are manifestations of how artificial talent is altering the way we function. What is often much less understood is the vast function synthetic brain can play in the social sector. The Artificial Intelligence for social good can probably assist in solving some of the country's most pressing problems. As a count number of facts, it can contribute in some way or every other to tackling and addressing all of the United Nation's Sustainable Development Goals, supporting large sections of the populace in both growing and developed countries. AI is already helping in several real-life situations, from assisting blind humans in navigating and diagnosing cancer to identify sexual harassment victims and helping with catastrophe relief. Let us take a look briefly at integral social domains where AI can be carried out effectively.

Psychological semantics is the study of how people represent the meanings of words and then build sentence meaning out of those representations. People use language dozens of time a day--to have conversations and give instructions, to read and write, to label objects and teach. A theory of psychological semantics must provide the basis for how people do all those things, choosing which words to use and understanding the words they read or hear. In this article we focus on the mental representation of word meaning. Human language is still the gold standard for a communication system, but artificial intelligence (AI) systems have made important progress in language use. Research on Natural Language Processing (NLP) develops systems that understand language to the degree that computers can carry out useful tasks. As described below, such systems use vast text corpora to learn about words, using neural networks and other statistical models. The recent explosion of research in NLP, driven largely by advances in neural networks (also called deep learning), has resulted in continuously improving performance on various benchmarks that require interpreting words and sentences. Systems are now used in interfaces with customers to make sales or solve problems.

Events are occurrences in specific locations, time, and semantics that nontrivially impact either our society or the nature, such as civil unrest, system failures, and epidemics. It is highly desirable to be able to anticipate the occurrence of such events in advance in order to reduce the potential social upheaval and damage caused. Event prediction, which has traditionally been prohibitively challenging, is now becoming a viable option in the big data era and is thus experiencing rapid growth. There is a large amount of existing work that focuses on addressing the challenges involved, including heterogeneous multi-faceted outputs, complex dependencies, and streaming data feeds. Most existing event prediction methods were initially designed to deal with specific application domains, though the techniques and evaluation procedures utilized are usually generalizable across different domains. However, it is imperative yet difficult to cross-reference the techniques across different domains, given the absence of a comprehensive literature survey for event prediction. This paper aims to provide a systematic and comprehensive survey of the technologies, applications, and evaluations of event prediction in the big data era. First, systematic categorization and summary of existing techniques are presented, which facilitate domain experts' searches for suitable techniques and help model developers consolidate their research at the frontiers. Then, comprehensive categorization and summary of major application domains are provided. Evaluation metrics and procedures are summarized and standardized to unify the understanding of model performance among stakeholders, model developers, and domain experts in various application domains. Finally, open problems and future directions for this promising and important domain are elucidated and discussed.

Parking is an inevitable issue in the fast-growing developing countries. Increasing number of vehicles require more and more urban land to be allocated for parking. However, a little attention has been conferred to the parking issues in developing countries like India. This study proposes a model for analysing the influence of car users' socioeconomic and travel characteristics on parking duration. Specifically, artificial neural networks (ANNs) is deployed to capture the interrelationship between driver characteristics and parking duration. ANNs are highly efficient in learning and recognizing connections between parameters for best prediction of an outcome. Since, utility of ANNs has been critically limited due to its Black Box nature, the study involves the use of Garson algorithm and Local interpretable model-agnostic explanations (LIME) for model interpretations. LIME shows the prediction for any classification, by approximating it locally with the developed interpretable model. This study is based on microdata collected on-site through interview surveys considering two land-uses: office-business and market/shopping. Results revealed the higher probability of prediction through LIME and therefore, the methodology can be adopted ubiquitously. Further, the policy implications are discussed based on the results for both land-uses. This unique study could lead to enhanced parking policy and management to achieve the sustainability goals.

Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. $\pm$1%) as NNs while achieving at least 10% improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.