Today, financial mobile applications and similar digital platforms need to provide much more than simple banking processes like payments and transactions, due to consumers' high expectations and an increasingly competitive e-banking industry. FIs already recognize that advanced technologies like artificial intelligence (AI), machine learning (ML), applied robotics, and biometrics are more and more relevant to deliver innovative products and services that cater to consumers' dynamic needs. These ever-changing needs require solid prioritization by FIs in terms of investment and shifting their budgets to the proper channels in hopes of overcoming the competition and delivering what their customers expect. A dramatic shift was shown in global priorities in the banking sector post-COVID-19, pertaining to 2020 and into 2021. The actual digital transformation stood out as a top priority for banks, with 75% of them acknowledging that these dire times are in critical need for them to fully switch their offerings to digital channels.

When San Francisco went into COVID-19 lockdown on March 17, the last thing 32-year-old tech entrepreneur Niket Desai had to worry about was staying fit. His regular spot, Barry's, would be closed indefinitely, but Desai had installed the Tempo Studio, an all-in-one home fitness device designed to turn 30 square feet of your living room into an artificial- intelligence-powered micro gym. Tempo is a six-foot-tall weight cabinet (weights included!) While similar devices, like Tonal, offer digital resistance training at home, Tempo is the first one to deploy 3D movement analysis, combined with machine learning and AI to improve your form and curate your workouts. Its screen streams more than 200 live and on-demand classes, from a ten-minute high-intensity workout to an hour of mobility training, while its motion sensors and AI isolate up to 25 different joints at 30 frames per second.

Growing up in a middle-class family in Kolkata and Midnapore in West Bengal, India, Dr Sayonsom Chanda was no stranger to strong winds and relentless rain knocking down electricity for hours, days, and even weeks. He and his family lived in East Midnapur through the horror of the 1999 Odisha cyclone and Sidr cyclone in 2007. It was one of the core reasons for him to start Sync Energy in 2017. The startup builds artificial intelligence (AI) tools that simplify emergency and disaster response planning for electric power distribution companies. The platform helps electric utilities reduce customer downtimes and be better informed about the impact of a disaster before it actually strikes. This, in-turn, will help electric power companies to decrease costs associated with emergency-related power outages.

There are several approaches which are used by Java Persistence API [12], [13], [14], Serialization mechanism [13] Multi-agent systems are often limited in terms of persistence, DBMS [14] and JADE Persistence Services [15]. This issue is more prevalent for applications in persistency framework did improve the flexibility and stability which agent states changes frequently. This makes the existing of an agent-based system however it increases the complexity methods less usable as they increase the agent's complexity of agents whose state changes in real-time. In the case when and are less scalable. This research study has presented a a certain object of agent is persisted in the database using novel in-memory agent persistence framework. Two prototypes composite keys, there is an increase in complexity to persist have been implemented, one using the proposed solution and and find the object. Increase in artifact size, framework complexity, the other using an established agent persistency environment. There is also a chance of Virtual Machine instance similar level of persistency. These findings will help future failure which will further increase the recovery time of the real-time multiagent systems to become scalable and persistent agent placed on a single instance due to VM churn time. in a dynamic cloud environment. However, when the data persistence is for a longer period or the state of the object frequently updates, the II. 2. I Moreover, when there is a change in many areas including aircraft maintenance, electronic book any data structure of the agent, the serialized object cannot be buying, network security, military logistic planning and maintaining deserialized even when you know the session id.

We present CoDEx, a set of knowledge graph Completion Datasets Extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. First, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from a popular link prediction benchmark by showing that CoDEx covers more diverse and interpretable content, and contains fewer relation patterns that can be covered by trivial frequency-based rules. Data, code, and pretrained models are available at https://github.com/tsafavi/codex.

Reasoning with declarative knowledge (RDK) and sequential decision-making (SDM) are two key research areas in artificial intelligence. RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning and reinforcement learning) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty. Despite the rich literature in these two areas, researchers have not fully explored their complementary strengths. In this paper, we survey algorithms that leverage RDK methods while making sequential decisions under uncertainty. We discuss significant developments, open problems, and directions for future work.

Competitions play an invaluable role in the field of forecasting, as exemplified through the recent M4 competition. The competition received attention from both academics and practitioners and sparked discussions around the representativeness of the data for business forecasting. Several competitions featuring real-life business forecasting tasks on the Kaggle platform has, however, been largely ignored by the academic community. We believe the learnings from these competitions have much to offer to the forecasting community and provide a review of the results from six Kaggle competitions. We find that most of the Kaggle datasets are characterized by higher intermittence and entropy than the M-competitions and that global ensemble models tend to outperform local single models. Furthermore, we find the strong performance of gradient boosted decision trees, increasing success of neural networks for forecasting, and a variety of techniques for adapting machine learning models to the forecasting task.

Estimating time-varying graphical models are of paramount importance in various social, financial, biological, and engineering systems, since the evolution of such networks can be utilized for example to spot trends, detect anomalies, predict vulnerability, and evaluate the impact of interventions. Existing methods require extensive tuning of parameters that control the graph sparsity and temporal smoothness. Furthermore, these methods are computationally burdensome with time complexity O(NP^3) for P variables and N time points. As a remedy, we propose a low-complexity tuning-free Bayesian approach, named BADGE. Specifically, we impose temporally-dependent spike-and-slab priors on the graphs such that they are sparse and varying smoothly across time. A variational inference algorithm is then derived to learn the graph structures from the data automatically. Owning to the pseudo-likelihood and the mean-field approximation, the time complexity of BADGE is only O(NP^2). Additionally, by identifying the frequency-domain resemblance to the time-varying graphical models, we show that BADGE can be extended to learning frequency-varying inverse spectral density matrices, and yields graphical models for multivariate stationary time series. Numerical results on both synthetic and real data show that that BADGE can better recover the underlying true graphs, while being more efficient than the existing methods, especially for high-dimensional cases.

Nonnegative Matrix Factorization (NMF) algorithms are fundamental tools in learning low-dimensional features from vector-valued data, Nonnegative Tensor Factorization (NTF) algorithms serve a similar role for dictionary learning problems for multi-modal data. Also, there is often a critical interest in \textit{online} versions of such factorization algorithms to learn progressively from minibatches, without requiring the full data as in conventional algorithms. However, the current theory of Online NTF algorithms is quite nascent, especially compared to the comprehensive literature on online NMF algorithms. In this work, we introduce a novel online NTF algorithm that learns a CP basis from a given stream of tensor-valued data under general constraints. In particular, using nonnegativity constraints, the learned CP modes also give localized dictionary atoms that respect the tensor structure in multi-model data. On the application side, we demonstrate the utility of our algorithm on a diverse set of examples from image, video, and time series data, illustrating how one may learn qualitatively different CP-dictionaries by not needing to reshape tensor data before the learning process. On the theoretical side, we prove that our algorithm converges to the set of stationary points of the objective function under the hypothesis that the sequence of data tensors have functional Markovian dependence. This assumption covers a wide range of application contexts including data streams generated by independent or MCMC sampling.

Most of the two-dimensional (2D) hydraulic/hydrodynamic models are still computationally too demanding for real-time applications. In this paper, an innovative modelling approach based on a deep convolutional neural network (CNN) method is presented for rapid prediction of fluvial flood inundation. The CNN model is trained using outputs from a 2D hydraulic model (i.e. LISFLOOD-FP) to predict water depths. The pre-trained model is then applied to simulate the January 2005 and December 2015 floods in Carlisle, UK. The CNN predictions are compared favourably with the outputs produced by LISFLOOD-FP. The performance of the CNN model is further confirmed by benchmarking against a support vector regression (SVR) method. The results show that the CNN model outperforms SVR by a large margin. The CNN model is highly accurate in capturing flooded cells as indicated by several quantitative assessment matrices. The estimated error for reproducing maximum flood depth is 0 ~ 0.2 meters for the 2005 event and 0 ~ 0.5 meters for the 2015 event at over 99% of the cells covering the computational domain. The proposed CNN method offers great potential for real-time flood modelling/forecasting considering its simplicity, superior performance and computational efficiency.