Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions.

Solving inverse problems is a fundamental component of science, engineering and mathematics. With the advent of deep learning, deep neural networks have significant potential to outperform existing state-of-the-art, model-based methods for solving inverse problems. However, it is known that current data-driven approaches face several key issues, notably hallucinations, instabilities and unpredictable generalization, with potential impact in critical tasks such as medical imaging. This raises the key question of whether or not one can construct deep neural networks for inverse problems with explicit stability and accuracy guarantees. In this work, we present a novel construction of accurate, stable and efficient neural networks for inverse problems with general analysis-sparse models, termed NESTANets. To construct the network, we first unroll NESTA, an accelerated first-order method for convex optimization. The slow convergence of this method leads to deep networks with low efficiency. Therefore, to obtain shallow, and consequently more efficient, networks we combine NESTA with a novel restart scheme. We then use compressed sensing techniques to demonstrate accuracy and stability. We showcase this approach in the case of Fourier imaging, and verify its stability and performance via a series of numerical experiments. The key impact of this work is demonstrating the construction of efficient neural networks based on unrolling with guaranteed stability and accuracy.

When the pandemic forced millions of people into working and collaborating remotely, it not only caused an explosion in the use and development of new technologies for productive and effective collaboration, it also made many of us more aware than ever of how technologies can enhance our thinking and creativity. At Nesta's Centre for Collective Intelligence Design, our work rests upon the premise that human intelligence combined with machine intelligence is more powerful than either in isolation. When these are successfully combined, it is known as collective intelligence. Our Grants Programme awarded funding to 15 different teams around the world that designed experiments to explore and test this idea in new ways to help tackle pressing social and environmental challenges. Each experiment fell under one of four themes: exploring artificial intelligence (AI)-crowd interaction; making better collective decisions; understanding the dynamics of collective behaviour; and gathering better data.

The Electrical Systems Division at the NASA Kennedy Space Center has developed and deployed an agent-based tool to monitor the space shuttle's ground processing telemetry stream. The agent provides autonomous monitoring of the telemetry stream and automatically alerts system engineers when predefined criteria have been met. Efficiency and safety are improved through increased automation. Sandia National Labs' Java Expert System Shell is employed as the rule engine. The shell's predicate logic lends itself well to capturing the heuristics and specifying the engineering rules of this spaceport domain.

China announced in 2017 its ambition to become the world leader in artificial intelligence (AI) by 2030. While the US still leads in absolute terms, China appears to be making more rapid progress than either the US or the EU, and central and local government spending on AI in China is estimated to be in the tens of billions of dollars. The move has led – at least in the West – to warnings of a global AI arms race and concerns about the growing reach of China's authoritarian surveillance state. But treating China as a "villain" in this way is both overly simplistic and potentially costly. While there are undoubtedly aspects of the Chinese government's approach to AI that are highly concerning and rightly should be condemned, it's important that this does not cloud all analysis of China's AI innovation.

It should have been artificial intelligence's moment in the sun. With billions of dollars of investment in recent years, AI has been touted as a solution to every conceivable problem. So when the COVID-19 pandemic arrived, a multitude of AI models were immediately put to work. Some hunted for new compounds that could be used to develop a vaccine, or attempted to improve diagnosis. Some tracked the evolution of the disease, or generated predictions for patient outcomes.

China announced in 2017 its ambition to become the world leader in artificial intelligence (AI) by 2030. While the US still leads in absolute terms, China appears to be making more rapid progress than either the US or the EU, and central and local government spending on AI in China is estimated to be in the tens of billions of dollars. The move has led – at least in the West – to warnings of a global AI arms race and concerns about the growing reach of China's authoritarian surveillance state. But treating China as a "villain" in this way is both overly simplistic and potentially costly. While there are undoubtedly aspects of the Chinese government's approach to AI that are highly concerning and rightly should be condemned, it's important that this does not cloud all analysis of China's AI innovation.

March is Women's History Month in the US, the UK and Australia, a time to honour women's sometimes underrated contributions to society. According to the US National Women's History Museum, Women's History Month started in 1978 as a local "Women's History Week" celebration in California, with organizers selecting the week to correspond with the March 8 International Women's Day. The US Congress in 1987 passed Public Law 100-9 designating March as the Women's History Month. The past few decades have seen a steady increase in the number of women studying and excelling in the STEM fields. But this is not so in computer science -- the number of women studying or pursuing a career in computer science has been decreasing since around 1990.

While it's perhaps prudent to take many of the doomsday predictions about the looming technological decimation of the labor market with a large pinch of salt, it is almost certain that whatever disruption does emerge will affect those in the most precarious position more than anyone. A recent report from the innovation group Nesta suggests that there are six million people in the U.K. who are in such a precarious position, and they caution that without assistance, these people will be stuck in a cycle of either low-pay and insecure employment or forced out of the workforce entirely. "The problem is that many people who are in low-paid work - or who aren't working at all - aren't able to access the information they need to plan for the future or the relevant training they need to gain new skills," the authors say. "They also tend to work in places and industries that are likely to lose out over the next decade, making it harder than ever for them to access good jobs." The challenge is compounded by the fact that those who are most at risk of disruption are also those least engaged with training and education.

In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into $3 \times 3$ batches and uses a hierarchy of Hamming Weight Compressors to process each batch. Besides, when processing the convolution across multiple channels, NESTA, rather than computing the precise result of a convolution per channel, quickly computes an approximation of its partial sum, and a residual value such that if added to the approximate partial sum, generates the accurate output. Then, instead of immediately adding the residual, it uses (consumes) the residual when processing the next batch in the hamming weight compressors with available capacity. This mechanism shortens the critical path by avoiding the need to propagate carry signals during each round of computation and speeds up the convolution of each channel. In the last stage of computation, when the partial sum of the last channel is computed, NESTA terminates by adding the residual bits to the approximate output to generate a correct result.