Accurate and reliable prediction of wind speed is a challenging task, because it depends on meteorological features of the surrounding region. In this work a novel Deep Ensemble Learning using Jet-like Architecture (DEL-Jet) approach is proposed. The proposed (DEL-Jet) technique is tested on wind speed prediction problem. As wind speed data is of the time series nature, so two Convolutional Neural Networks (CNNs) in addition to a deep Auto-Encoder (AE) are used to extract the feature space from input data. Whereas, Non-linear Principal Component Analysis (NLPCA) is employed to further reduce the dimensionality of extracted feature space. Finally, reduced feature space along with original feature space are used to train the meta-regressor for forecasting final wind speed. To show the effectiveness of work, performance of the proposed DEL-Jet technique is evaluated for ten independent runs and compared against commonly used regressors.

Most existing crowd counting methods require object location-level annotation, i.e., placing a dot at the center of an object. While being simpler than the bounding-box or pixel-level annotation, obtaining this annotation is still labor-intensive and time-consuming especially for images with highly crowded scenes. On the other hand, weaker annotations that only know the total count of objects can be almost effortless in many practical scenarios. Thus, it is desirable to develop a learning method that can effectively train models from count-level annotations. To this end, this paper studies the problem of weakly-supervised crowd counting which learns a model from only a small amount of location-level annotations (fully-supervised) but a large amount of count-level annotations (weakly-supervised). To perform effective training in this scenario, we observe that the direct solution of regressing the integral of density map to the object count is not sufficient and it is beneficial to introduce stronger regularizations on the predicted density map of weakly-annotated images. We devise a simple-yet-effective training strategy, namely Multiple Auxiliary Tasks Training (MATT), to construct regularizes for restricting the freedom of the generated density maps. Through extensive experiments on existing datasets and a newly proposed dataset, we validate the effectiveness of the proposed weakly-supervised method and demonstrate its superior performance over existing solutions.

Recent surveys, studies, forecasts and other quantitative assessments of the progress of AI highlight the increasing presence of AI in the healthcare industry, the assistance AI may provide in the future to workers' cognitive tasks, and the continuing acceleration in data production and dissemination. Of the $27 billion raised, U.S. startups accounted for $17 billion, up from $13.3 billion the previous year. Chinese AI startups, on the other hand, raised only $2.9 billion in 2019, down from $4.7 billion in 2018. Big companies wouldn't be investing billions [in AI] if it wasn't producing for them"--Geoffrey Hinton "Artificial intelligence enables us to process the vast quantity of data across our businesses to generate new insights which can keep us ahead of the competition"--Yuri Sebregts, chief technology officer, Shell

Trust, transparency and technology: helping your employees embrace AI. If we look at today's workforce like a traditional family unit, employees can feel like the proverbial middle child, often overlooked in order to respond to the louder demands of the younger child and never given the same trusted responsibilities of an elder child. Business leaders, like busy parents, can tend to focus on keeping their key stakeholders, investors and customers happy while considering their employees as an afterthought. However, with the rapid digital transformation of today's workplace, employers need to focus more on reassuring their employees as they deal with change and uncertainty. This was reinforced in a recent survey of employers by Genesys, revealing a belief that more than half of employees (52 per cent) have concerns their jobs may be eliminated as a result of advanced technologies, like artificial intelligence (AI) and bots.

In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with generic MCMC kernels, but is especially well suited to \textit{MetFlow}, a novel family of MCMC algorithms we introduce, in which proposals are obtained using Normalizing Flows. The marginal distribution produced by such MCMC algorithms is a mixture of flow-based distributions, thus drastically increasing the expressivity of the variational family. Unlike previous methods following this direction, our approach is amenable to the reparametrization trick and does not rely on computationally expensive reverse kernels. Extensive numerical experiments show clear computational and performance improvements over state-of-the-art methods.

We present a modular neural network architecture MAIN that learns algorithms given a set of input-output examples. MAIN consists of a neural controller that interacts with a variable-length input tape and learns to compose modules together with their corresponding argument choices. Unlike previous approaches, MAIN uses a general domain-agnostic mechanism for selection of modules and their arguments. It uses a general input tape layout together with a parallel history tape to indicate most recently used locations. Finally, it uses a memoryless controller with a length-invariant self-attention based input tape encoding to allow for random access to tape locations. The MAIN architecture is trained end-to-end using reinforcement learning from a set of input-output examples. We evaluate MAIN on five algorithmic tasks and show that it can learn policies that generalizes perfectly to inputs of much longer lengths than the ones used for training.

Zero-sum games have long guided artificial intelligence research, since they possess both a rich strategy space of best-responses and a clear evaluation metric. What's more, competition is a vital mechanism in many real-world multi-agent systems capable of generating intelligent innovations: Darwinian evolution, the market economy and the AlphaZero algorithm, to name a few. In two-player zero-sum games, the challenge is usually viewed as finding Nash equilibrium strategies, safeguarding against exploitation regardless of the opponent. While this captures the intricacies of chess or Go, it avoids the notion of cooperation with co-players, a hallmark of the major transitions leading from unicellular organisms to human civilization. Beyond two players, alliance formation often confers an advantage; however this requires trust, namely the promise of mutual cooperation in the face of incentives to defect. Successful play therefore requires adaptation to co-players rather than the pursuit of non-exploitability. Here we argue that a systematic study of many-player zero-sum games is a crucial element of artificial intelligence research. Using symmetric zero-sum matrix games, we demonstrate formally that alliance formation may be seen as a social dilemma, and empirically that na\"ive multi-agent reinforcement learning therefore fails to form alliances. We introduce a toy model of economic competition, and show how reinforcement learning may be augmented with a peer-to-peer contract mechanism to discover and enforce alliances. Finally, we generalize our agent model to incorporate temporally-extended contracts, presenting opportunities for further work.

Multivariate Hawkes Processes (MHPs) are an important class of temporal point processes that have enabled key advances in understanding and predicting social information systems. However, due to their complex modeling of temporal dependencies, MHPs have proven to be notoriously difficult to scale, what has limited their applications to relatively small domains. In this work, we propose a novel model and computational approach to overcome this important limitation. By exploiting a characteristic sparsity pattern in real-world diffusion processes, we show that our approach allows to compute the exact likelihood and gradients of an MHP -- independently of the ambient dimensions of the underlying network. We show on synthetic and real-world datasets that our model does not only achieve state-of-the-art predictive results, but also improves runtime performance by multiple orders of magnitude compared to standard methods on sparse event sequences. In combination with easily interpretable latent variables and influence structures, this allows us to analyze diffusion processes at previously unattainable scale.

In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact {\em biased} compressors often show superior performance in practice when compared to the much more studied and understood {\em unbiased} compressors, very little is known about them. In this work we study three classes of biased compression operators, two of which are new, and their performance when applied to (stochastic) gradient descent and distributed (stochastic) gradient descent. We show for the first time that biased compressors can lead to linear convergence rates both in the single node and distributed settings. Our {\em distributed} SGD method enjoys the ergodic rate $\mathcal{O}\left(\frac{\delta L \exp(-K) }{\mu} + \frac{(C + D)}{K\mu}\right)$, where $\delta$ is a compression parameter which grows when more compression is applied, $L$ and $\mu$ are the smoothness and strong convexity constants, $C$ captures stochastic gradient noise ($C=0$ if full gradients are computed on each node) and $D$ captures the variance of the gradients at the optimum ($D=0$ for over-parameterized models). Further, via a theoretical study of several synthetic and empirical distributions of communicated gradients, we shed light on why and by how much biased compressors outperform their unbiased variants. Finally, we propose a new highly performing biased compressor---combination of Top-$k$ and natural dithering---which in our experiments outperforms all other compression techniques.

A Machine can only learn if it is biased in some way. Typically the bias is supplied by hand, for example through the choice of an appropriate set of features. However, if the learning machine is embedded within an {\em environment} of related tasks, then it can {\em learn} its own bias by learning sufficiently many tasks from the environment. In this paper two models of bias learning (or equivalently, learning to learn) are introduced and the main theoretical results presented. The first model is a PAC-type model based on empirical process theory, while the second is a hierarchical Bayes model.