Building on recent research for prediction of hurricane trajectories using recurrent neural networks (RNNs), we have developed improved methods and generalized the approach to predict Bayesian intervals in addition to simple point estimates. Tropical storms are capable of causing severe damage, so accurately predicting their trajectories can bring significant benefits to cities and lives, especially as they grow more intense due to climate change effects. By implementing the Bayesian interval using dropout in an RNN, we improve the actionability of the predictions, for example by estimating the areas to evacuate in the landfall region. We used an RNN to predict the trajectory of the storms at 6-hour intervals. We used latitude, longitude, windspeed, and pressure features from a Statistical Hurricane Intensity Prediction Scheme (SHIPS) dataset of about 500 tropical storms in the Atlantic Ocean.

Multi-model ensemble analysis integrates information from multiple climate models into a unified projection. However, existing integration approaches based on model averaging can dilute fine-scale spatial information and incur bias from rescaling low-resolution climate models. We propose a statistical approach, called NN-GPR, using Gaussian process regression (GPR) with an infinitely wide deep neural network based covariance function. NN-GPR requires no assumptions about the relationships between models, no interpolation to a common grid, no stationarity assumptions, and automatically downscales as part of its prediction algorithm. Model experiments show that NN-GPR can be highly skillful at surface temperature and precipitation forecasting by preserving geospatial signals at multiple scales and capturing inter-annual variability. Our projections particularly show improved accuracy and uncertainty quantification skill in regions of high variability, which allows us to cheaply assess tail behavior at a 0.44$^\circ$/50 km spatial resolution without a regional climate model (RCM). Evaluations on reanalysis data and SSP245 forced climate models show that NN-GPR produces similar, overall climatologies to the model ensemble while better capturing fine scale spatial patterns. Finally, we compare NN-GPR's regional predictions against two RCMs and show that NN-GPR can rival the performance of RCMs using only global model data as input.

Artificial intelligence (AI) features are increasingly being embedded in cars and are central to the operation of self-driving cars (SDC). There is little or no effort expended towards understanding and assessing the broad legal and regulatory impact of the decisions made by AI in cars. A comprehensive literature review was conducted to determine the perceived barriers, benefits and facilitating factors of SDC in order to help us understand the suitability and limitations of existing and proposed law and regulation. (1) existing and proposed laws are largely based on claimed benefits of SDV that are still mostly speculative and untested; (2) while publicly presented as issues of assigning blame and identifying who pays where the SDC is involved in an accident, the barriers broadly intersect with almost every area of society, laws and regulations; and (3) new law and regulation are most frequently identified as the primary factor for enabling SDC. Research on assessing the impact of AI in SDC needs to be broadened beyond negligence and liability to encompass barriers, benefits and facilitating factors identified in this paper. Results of this paper are significant in that they point to the need for deeper comprehension of the broad impact of all existing law and regulations on the introduction of SDC technology, with a focus on identifying only those areas truly requiring ongoing legislative attention.

In this paper, a deep convolutional neural network-based symbol detection and demodulation is proposed for generalized frequency division multiplexing with index modulation (GFDM-IM) scheme in order to improve the error performance of the system. The proposed method first pre-processes the received signal by using a zero-forcing (ZF) detector and then uses a neural network consisting of a convolutional neural network (CNN) followed by a fully-connected neural network (FCNN). The FCNN part uses only two fully-connected layers, which can be adapted to yield a trade-off between complexity and bit error rate (BER) performance. This two-stage approach prevents the getting stuck of neural network in a saddle point and enables IM blocks processing independently. It has been demonstrated that the proposed deep convolutional neural network-based detection and demodulation scheme provides better BER performance compared to ZF detector with a reasonable complexity increase. We conclude that non-orthogonal waveforms combined with IM schemes with the help of deep learning is a promising physical layer (PHY) scheme for future wireless networks

In this paper, deep learning (DL)-aided data detection of spatial multiplexing (SMX) multiple-input multiple-output (MIMO) transmission with index modulation (IM) (Deep-SMX-IM) has been proposed. Deep-SMX-IM has been constructed by combining a zero-forcing (ZF) detector and DL technique. The proposed method uses the significant advantages of DL techniques to learn transmission characteristics of the frequency and spatial domains. Furthermore, thanks to using subblockbased detection provided by IM, Deep-SMX-IM is a straightforward method, which eventually reveals reduced complexity. It has been shown that Deep-SMX-IM has significant error performance gains compared to ZF detector without increasing computational complexity for different system configurations.

I never read original papers of the greatest scientists, but I got so intrigued by the information theory that I gave Claude Shannon's seminal paper a read. In this single paper, Shannon introduced this new fundamental theory. He raised the right questions, which no one else even thought of asking. This would have been enough to make this contribution earthshaking. But amazingly enough, Shannon also provided most of the right answers with class and elegance. In comparison, it took decades for a dozen of top physicists to define the basics of quantum theory. Meanwhile, Shannon constructed something equivalent, all by himself, in a single paper. Shannon's theory has since transformed the world like no other ever had, from information technologies to telecommunications, from theoretical physics to economical globalization, from everyday life to philosophy. I don't think Shannon has had the credits he deserves.

Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily assessed, whereas judging that from their spelling is often impossible (e.g. cat /feline) and to predetermine and store similarities between all words is prohibitively time-consuming, memory intensive and subjective. We focus on word embeddings learned from text corpora and knowledge graphs. Several well-known algorithms learn word embeddings from text on an unsupervised basis by learning to predict those words that occur around each word, e.g. word2vec and GloVe. Parameters of such word embeddings are known to reflect word co-occurrence statistics, but how they capture semantic meaning has been unclear. Knowledge graph representation models learn representations both of entities (words, people, places, etc.) and relations between them, typically by training a model to predict known facts in a supervised manner. Despite steady improvements in fact prediction accuracy, little is understood of the latent structure that enables this. The limited understanding of how latent semantic structure is encoded in the geometry of word embeddings and knowledge graph representations makes a principled means of improving their performance, reliability or interpretability unclear. To address this: 1. we theoretically justify the empirical observation that particular geometric relationships between word embeddings learned by algorithms such as word2vec and GloVe correspond to semantic relations between words; and 2. we extend this correspondence between semantics and geometry to the entities and relations of knowledge graphs, providing a model for the latent structure of knowledge graph representation linked to that of word embeddings.

Encoding facts as representations of entities and binary relationships between them, as learned by knowledge graph representation models, is useful for various tasks, including predicting new facts, question answering, fact checking and information retrieval. The focus of this thesis is on (i) improving knowledge graph representation with the aim of tackling the link prediction task; and (ii) devising a theory on how semantics can be captured in the geometry of relation representations. Most knowledge graphs are very incomplete and manually adding new information is costly, which drives the development of methods which can automatically infer missing facts. The first contribution of this thesis is HypER, a convolutional model which simplifies and improves upon the link prediction performance of the existing convolutional state-of-the-art model ConvE and can be mathematically explained in terms of constrained tensor factorisation. The second contribution is TuckER, a relatively straightforward linear model, which, at the time of its introduction, obtained state-of-the-art link prediction performance across standard datasets. The third contribution is MuRP, first multi-relational graph representation model embedded in hyperbolic space. MuRP outperforms all existing models and its Euclidean counterpart MuRE in link prediction on hierarchical knowledge graph relations whilst requiring far fewer dimensions. Despite the development of a large number of knowledge graph representation models with gradually increasing predictive performance, relatively little is known of the latent structure they learn. We generalise recent theoretical understanding of how semantic relations of similarity, paraphrase and analogy are encoded in the geometric interactions of word embeddings to how more general relations, as found in knowledge graphs, can be encoded in their representations.

This means that the contribution of wind power in power systems is becoming increasingly important. The downside is that detailed schedule plans and reserve capacity must be properly set by power system regulators (Impram et al., 2020) facing the intrinsic problem of the highly intermittent nature of wind, making this very hard to predict. The accuracy of wind forecasts thus becomes an issue of paramount importance for the wind industry. In a recent work by Casciaro et al. (2021), a novel accurate Ensemble Model Output Statistics (EMOS) strategy for calibrating wind speed/power forecasts from an Ensemble Prediction System (EPS) has been proposed and its superiority when compared against more parsimonious strategies in the 0-48 h look-ahead forecast horizon clearly emerged. However, because all global weather models start their run from analysis corresponding to the main synoptic hours 00, 06, 12, and 18 UTC, weather predictions (of any forecast horizons) necessarily remain frozen for six hours.

The benefits of analytics are well-documented. Analytics has helped organisations transform retail experiences, map pathways for trains and trucks, discover extraterrestrial life, and even predict diseases. However, over the past few years, organisations across the globe have wrestled with just how much human error has permeated their analytics attempts, often ending with disastrous results. From crashing spacecraft to sinking ships, transferring billions of dollars to unintended recipients, and causing deaths due to overdose of medication, human error in data analysis has far-reaching ramifications for organisations. The reason for human error in data analysis could be many, such as lack of experience, fatigue or loss of attention, lack of knowledge, or the all-too-common biases in interpreting data. However, what's common among these errors is that they are related to humans reading, processing, analysing, and interpreting data.