"AlphaZero crushes chess!" scream the headlinesa as the AlphaZero algorithm developed by Google and DeepMind took just four hours of playing against itself (with no human help) to defeat the reigning World Computer Champion Stockfish by 28 wins to 0 in a 100-game match. Only four hours to recreate the chess knowledge of one and a half millennium of human creativity! This followed the announcement just weeks earlier that their program AlphaGoZero had, starting from scratch, with no human inputs at all, comprehensively beaten the previous version AlphaGo, which in turn had spectacularly beaten one of the world's top Go players, Lee Seedol, 4-1 in a match in Seoul, Korea, in March 2016. Interest in AI has reached fever pitch in the popular imagination--its opportunities and its threats. The time is ripe for books on AI and what it holds for our future such as Life 3.0: Being Human in the Age of Artificial Intelligence by Max Tegmark, Android Dreams by Toby Walsh, and Artificial Intelligence by Melanie Mitchell.6,8,9

Imagine that you're asked to finish this sentence: "Two Muslims walked into a …" Which word would you add? "Bar," maybe? It sounds like the start of a joke. But when Stanford researchers fed the unfinished sentence into GPT-3, an artificial intelligence system that generates text, the AI completed the sentence in distinctly unfunny ways. "Two Muslims walked into a synagogue with axes and a bomb," it said. Or, on another try, "Two Muslims walked into a Texas cartoon contest and opened fire."

Compute requirements at the edge, such as the resource footprint of endpoints/edge devices & performance KPIs of Internet of Things applications make optimization of Deep Neural Networks (DNNs) critical for deployment. By deployment we assume that the Deep Learning (DL) model gets fixed in all aspects (e.g., task definition, dataset, training pipeline, etc.) so it can speed up model inferencing presuming the rest of the flow is equal. There are two main objectives for model optimization: reduction of the model size and decreasing computational complexity and both are highly correlated with each other. For example, reduction of the model size in many cases leads to less memory consumption and thus latency reduction, which, in turn, improves performance. Nowadays, many optimization methods have been proposed to tackle both objectives. Perhaps, uniform quantization is one of the simple methods to do that because it leads to a small accuracy drop, substantial reduction in the model size, and significant performance speedup can be applied even without retraining or fine-tuning the optimizing model.

Kristóf is Founder and CTO at Turbine.AI, and holds a PhD in molecular biology and bioinformatics. To inquire about contributed articles from outside experts, contact editorial@emerj.com. Could you predict how an airplane flies only based on an inventory of its parts? This – with proteins – is the essence of the protein folding challenge. Two weeks ago, the organizers of the CASP protein folding challenge just announced that DeepMind's AlphaFold essentially solved the challenge – its prediction score was just below experimental error.

Remaining useful life (RUL) refers to the expected remaining lifespan of a component or system. Accurate RUL prediction is critical for prognostic and health management and for maintenance planning. In this work, we address three prevalent challenges in data-driven RUL prediction, namely the handling of high dimensional input features, the robustness to noise in sensor data and prognostic datasets, and the capturing of the time-dependency between system degradation and RUL prediction. We devise a highly accurate RUL prediction model with uncertainty quantification, which integrates and leverages the advantages of deep learning and nonstationary Gaussian process regression (DL-NSGPR). We examine and benchmark our model against other advanced data-driven RUL prediction models using the turbofan engine dataset from the NASA prognostic repository. Our computational experiments show that the DL-NSGPR predictions are highly accurate with root mean square error 1.7 to 6.2 times smaller than those of competing RUL models. Furthermore, the results demonstrate that RUL uncertainty bounds with the proposed DL-NSGPR are both valid and significantly tighter than other stochastic RUL prediction models. We unpack and discuss the reasons for this excellent performance of the DL-NSGPR.

An entity mention in text such as "Washington" may correspond to many different named entities such as the city "Washington D.C." or the newspaper "Washington Post." The goal of named entity disambiguation is to identify the mentioned named entity correctly among all possible candidates. If the type (e.g. location or person) of a mentioned entity can be correctly predicted from the context, it may increase the chance of selecting the right candidate by assigning low probability to the unlikely ones. This paper proposes cluster-based mention typing for named entity disambiguation. The aim of mention typing is to predict the type of a given mention based on its context. Generally, manually curated type taxonomies such as Wikipedia categories are used. We introduce cluster-based mention typing, where named entities are clustered based on their contextual similarities and the cluster ids are assigned as types. The hyperlinked mentions and their context in Wikipedia are used in order to obtain these cluster-based types. Then, mention typing models are trained on these mentions, which have been labeled with their cluster-based types through distant supervision. At the named entity disambiguation phase, first the cluster-based types of a given mention are predicted and then, these types are used as features in a ranking model to select the best entity among the candidates. We represent entities at multiple contextual levels and obtain different clusterings (and thus typing models) based on each level. As each clustering breaks the entity space differently, mention typing based on each clustering discriminates the mention differently. When predictions from all typing models are used together, our system achieves better or comparable results based on randomization tests with respect to the state-of-the-art levels on four defacto test sets.

After decades of massive digitisation, an unprecedented amount of historical documents is available in digital format, along with their machine-readable texts. While this represents a major step forward with respect to preservation and accessibility, it also opens up new opportunities in terms of content mining and the next fundamental challenge is to develop appropriate technologies to efficiently search, retrieve and explore information from this 'big data of the past'. Among semantic indexing opportunities, the recognition and classification of named entities are in great demand among humanities scholars. Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical and noisy inputs. In this survey, we present the array of challenges posed by historical documents to NER, inventory existing resources, describe the main approaches deployed so far, and identify key priorities for future developments.

In recent years a large literature on deep learning based methods for the numerical solution partial differential equations has emerged; results for integro-differential equations on the other hand are scarce. In this paper we study deep neural network algorithms for solving linear and semilinear parabolic partial integro-differential equations with boundary conditions in high dimension. To show the viability of our approach we discuss several case studies from insurance and finance.

The prospect of achieving quantum advantage with Quantum Neural Networks (QNNs) is exciting. Understanding how QNN properties (e.g., the number of parameters $M$) affect the loss landscape is crucial to the design of scalable QNN architectures. Here, we rigorously analyze the overparametrization phenomenon in QNNs with periodic structure. We define overparametrization as the regime where the QNN has more than a critical number of parameters $M_c$ that allows it to explore all relevant directions in state space. Our main results show that the dimension of the Lie algebra obtained from the generators of the QNN is an upper bound for $M_c$, and for the maximal rank that the quantum Fisher information and Hessian matrices can reach. Underparametrized QNNs have spurious local minima in the loss landscape that start disappearing when $M\geq M_c$. Thus, the overparametrization onset corresponds to a computational phase transition where the QNN trainability is greatly improved by a more favorable landscape. We then connect the notion of overparametrization to the QNN capacity, so that when a QNN is overparametrized, its capacity achieves its maximum possible value. We run numerical simulations for eigensolver, compilation, and autoencoding applications to showcase the overparametrization computational phase transition. We note that our results also apply to variational quantum algorithms and quantum optimal control.

Deep-learning based Automatic Essay Scoring (AES) systems are being actively used by states and language testing agencies alike to evaluate millions of candidates for life-changing decisions ranging from college applications to visa approvals. However, little research has been put to understand and interpret the black-box nature of deep-learning based scoring algorithms. Previous studies indicate that scoring models can be easily fooled. In this paper, we explore the reason behind their surprising adversarial brittleness. We utilize recent advances in interpretability to find the extent to which features such as coherence, content, vocabulary, and relevance are important for automated scoring mechanisms. We use this to investigate the oversensitivity i.e., large change in output score with a little change in input essay content) and overstability i.e., little change in output scores with large changes in input essay content) of AES. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models with rich contextual embeddings such as BERT, behave like bag-of-words models. A few words determine the essay score without the requirement of any context making the model largely overstable. This is in stark contrast to recent probing studies on pre-trained representation learning models, which show that rich linguistic features such as parts-of-speech and morphology are encoded by them. Further, we also find that the models have learnt dataset biases, making them oversensitive. To deal with these issues, we propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies. We find that our proposed models are able to detect unusual attribution patterns and flag adversarial samples successfully.