Propaganda aims at influencing people's mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at the document level, typically labelling all articles from a propagandistic news outlet as propaganda. Such noisy gold labels inevitably affect the quality of any learning system trained on them. A further issue with most existing systems is the lack of explainability. To overcome these limitations, we propose a novel task: performing fine-grained analysis of texts by detecting all fragments that contain propaganda techniques as well as their type. In particular, we create a corpus of news articles manually annotated at the fragment level with eighteen propaganda techniques and we propose a suitable evaluation measure. We further design a novel multi-granularity neural network, and we show that it outperforms several strong BERT-based baselines.

Many systems require optimisation over multiple objectives, where objectives are characteristics of the system such as energy consumed or increase in time to perform the work. Optimisation is performed by selecting the `best' set of input parameters to elicit the desired objectives. However, the parameter search space can often be far larger than can be searched in a reasonable time. Additionally, the objectives are often mutually exclusive -- leading to a decision being made as to which objective is more important or optimising over a combination of the objectives. This work is an application of a Genetic Algorithm to identify the Pareto frontier for finding the optimal parameter sets for all combinations of objectives. A Pareto frontier can be used to identify the sets of optimal parameters for which each is the `best' for a given combination of objectives -- thus allowing decisions to be made with full knowledge. We demonstrate this approach for the HTC-Sim simulation system in the case where a Reinforcement Learning scheduler is tuned for the two objectives of energy consumption and task overhead. Demonstrating that this approach can reduce the energy consumed by ~36% over previously published work without significantly increasing the overhead.

The parameters are usually fitted only on the basis of experimental results. The squashing function (also soft cutting or soft clipping function) introduced above stands out of the other candidates by having a theoretical background thanks to the nilpotent logic which lies behind the scenes. In, 17 Klimek and Perelstein presented a Neural Network (NN) algorithm optimized to perform a Monte Carlo methods, which are widely used in particle physics to integrate and sample probability distributions on multidimensional phase spaces. The algorithm has been applied to several examples of direct relevance for particle physics, including situations with nontrivial features such as sharp resonances and soft/collinear enhancements. In this algorithm, each node in a hidden layer of the NN takes a linear combination of the outputs of the nodes in the previous layer and applies an activation function.

A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise due to the uncertain environment in which AVs operate such as road and weather conditions, errors in perception and sensory data, and also model inaccuracy. In this paper, we propose a system architecture for risk-aware AVs capable of reasoning about uncertainty and deliberately bounding the risk of collision below a given threshold. We discuss key challenges in the area, highlight recent research developments, and propose future research directions in three subsystems. First, a perception subsystem that detects objects within a scene while quantifying the uncertainty that arises from different sensing and communication modalities. Second, an intention recognition subsystem that predicts the driving-style and the intention of agent vehicles (and pedestrians). Third, a planning subsystem that takes into account the uncertainty, from perception and intention recognition subsystems, and propagates all the way to control policies that explicitly bound the risk of collision. We believe that such a white-box approach is crucial for future adoption of AVs on a large scale.

We discuss the problem of defining a logic for analogical reasoning, and sketch a solution in the style of the semantics for Counterfactual Conditionals, Preferential Structures, etc.

We propose a new aggregation framework for approximate dynamic programming, which provides a connection with rollout algorithms, approximate policy iteration, and other single and multistep lookahead methods. The central novel characteristic is the use of a bias function $V$ of the state, which biases the values of the aggregate cost function towards their correct levels. The classical aggregation framework is obtained when $V\equiv0$, but our scheme works best when $V$ is a known reasonably good approximation to the optimal cost function $J^*$. When $V$ is equal to the cost function $J_{\mu}$ of some known policy $\mu$ and there is only one aggregate state, our scheme is equivalent to the rollout algorithm based on $\mu$ (i.e., the result of a single policy improvement starting with the policy $\mu$). When $V=J_{\mu}$ and there are multiple aggregate states, our aggregation approach can be used as a more powerful form of improvement of $\mu$. Thus, when combined with an approximate policy evaluation scheme, our approach can form the basis for a new and enhanced form of approximate policy iteration. When $V$ is a generic bias function, our scheme is equivalent to approximation in value space with lookahead function equal to $V$ plus a local correction within each aggregate state. The local correction levels are obtained by solving a low-dimensional aggregate DP problem, yielding an arbitrarily close approximation to $J^*$, when the number of aggregate states is sufficiently large. Except for the bias function, the aggregate DP problem is similar to the one of the classical aggregation framework, and its algorithmic solution by simulation or other methods is nearly identical to one for classical aggregation, assuming values of $V$ are available when needed.

Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework with improved shared-private memory. The shared memory learns common features among different languages and facilitates a cross-lingual transfer to boost dialogue systems, while the private memory is owned by each separate language to capture its unique feature. Experiments conducted on Chinese and English conversation corpora of different scales show that our proposed architecture outperforms the individually learned model with the help of the other language, where the improvement is particularly distinct when the training data is limited.

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. The agent needs to learn a latent representation together with a control policy to perform the task. Fitting a high-capacity encoder using a scarce reward signal is not only sample inefficient, but also prone to suboptimal convergence. Two ways to improve sample efficiency are to extract relevant features for the task and use off-policy algorithms. We dissect various approaches of learning good latent features, and conclude that the image reconstruction loss is the essential ingredient that enables efficient and stable representation learning in image-based RL. Following these findings, we devise an off-policy actor-critic algorithm with an auxiliary decoder that trains end-to-end and matches state-of-the-art performance across both model-free and model-based algorithms on many challenging control tasks. We release our code to encourage future research on image-based RL.

The rise of artificial intelligence (AI) is one of the defining business opportunities for leaders today. Closely associated with it: the challenge of creating an organization that can rise to that opportunity and exploit the potential of AI at scale. Meeting this challenge requires organizations to prepare their leaders, business staff, analytics teams, and end users to work and think in new ways--not only by helping these cohorts understand how to tap into AI effectively, but also by teaching them to embrace data exploration, agile development, and interdisciplinary teamwork. Often, companies use an ad hoc approach to their talent-building efforts. They hire new workers equipped with these skills in spurts and rely on online-learning platforms, universities, and executive-level programs to train existing employees.

Artificial intelligence generated writing and similar tools are offering journalists a second chance to reconnect with the public and up-their-game, according to Charlie Becket. The researcher is director of the Media Policy Project, sponsored by the London School of Economics and Political Science. "AI in its broadest sense provides all sorts of opportunities for journalism – and journalism needs all the help it can get right now," Beckett says. The reason: "A few years ago, a couple of companies said they would be able to replace journalists within a few years, Van der Lee, says. It's a boast that turned out to be untrue. Instead, AI systems like Van der Lee's – which can generate short sports stories, which detail results of thousands of local soccer matches on a regular basis – are all about doing rote work. That frees-up journalists to write more complex, more insightful news stories and features, according to Van der Lee. "Robots will never write as well as people," Van der Lee says. It's an AI editor that works in popular Web browsers. The new feature on the AI editing tool can offer suggestions to create a writing tone that is neutral, confident, joyful, optimistic, friendly, urgent, analytical or respectful. Currently, Grammarly's tone analysis is available for Google Chrome users only. The toolmaker's plan in coming months is to roll-out the feature to Firefox, Safari and other popular browsers. It's a step-by-step guide on how to get started using AI-generated writing for public relations, marketing and similar endeavors in content generation. "Today, instead of three-to-five hours, reports take us 10 minutes to write," Moehring says. "The reports are delivered on the first business day of the month.