Deep Reinforcement Learning (RL) has considerably advanced over the past decade. At the same time, state-of-the-art RL algorithms require a large computational budget in terms of training time to converge. Recent work has started to approach this problem through the lens of quantum computing, which promises theoretical speed-ups for several traditionally hard tasks. In this work, we examine a class of hybrid quantumclassical RL algorithms that we collectively refer to as variational quantum deep Q-networks (VQ-DQN). We show that VQ-DQN approaches are subject to instabilities that cause the learned policy to diverge, study the extent to which this afflicts reproduciblity of established results based on classical simulation, and perform systematic experiments to identify potential explanations for the observed instabilities. Additionally, and in contrast to most existing work on quantum reinforcement learning, we execute RL algorithms on an actual quantum processing unit (an IBM Quantum Device) and investigate differences in behaviour between simulated and physical quantum systems that suffer from implementation deficiencies. Our experiments show that, contrary to opposite claims in the literature, it cannot be conclusively decided if known quantum approaches, even if simulated without physical imperfections, can provide an advantage as compared to classical approaches. Finally, we provide a robust, universal and well-tested implementation of VQ-DQN as a reproducible testbed for future experiments.

We give exponential statistical query (SQ) lower bounds for learning two-hidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free) model. No general SQ lower bounds were known for learning ReLU networks of any depth in this setting: previous SQ lower bounds held only for adversarial noise models (agnostic learning) or restricted models such as correlational SQ. Prior work hinted at the impossibility of our result: Vempala and Wilmes showed that general SQ lower bounds cannot apply to any real-valued family of functions that satisfies a simple non-degeneracy condition. To circumvent their result, we refine a lifting procedure due to Daniely and Vardi that reduces Boolean PAC learning problems to Gaussian ones. We show how to extend their technique to other learning models and, in many well-studied cases, obtain a more efficient reduction. As such, we also prove new cryptographic hardness results for PAC learning two-hidden-layer ReLU networks, as well as new lower bounds for learning constant-depth ReLU networks from membership queries.

The EU strikes again with a new set of regulations that take aim at the use of artificial intelligence (AI) to address the variety of risks associated with the societal adoption of AI. Like its sibling the General Data Protection Regulation (GDPR), the Artificial Intelligence Act (AIA) actually has teeth, with fines rising to €30 million, or 6% of global revenue. Is the answer to delete all your AI systems to minimize your risk to zero, or continue using AI for a competitive edge? Can you manage the recurring costs required to maintain compliance with the AIA even as the technology itself increases your bottomline? Take the famous UK pub chain JD Wetherspoon, founded by British businessman Tim Martin in 1979 who has been an outspoken critic of the EU and a Brexit campaigner. Their response to personal identifiable information (PII) protection, legislated by the GDPR in 2017, was to delete their entire CRM database.

This article proposes an architecture, which allows the prediction of intention by internally simulating perceptual states represented by action pattern vectors. To this end, associative self-organising neural networks (A-SOM) is utilised to build a hierarchical cognitive architecture for recognition and simulation of the skeleton based human actions. The abilities of the proposed architecture in recognising and predicting actions is evaluated in experiments using three different datasets of 3D actions. Based on the experiments of this article, applying internally simulated perceptual states represented by action pattern vectors improves the performance of the recognition task in all experiments. Furthermore, internal simulation of perception addresses the problem of having limited access to the sensory input, and also the future prediction of the consecutive perceptual sequences. The performance of the system is compared and discussed with similar architecture using self-organizing neural networks (SOM).

The task of Outside Knowledge Visual Question Answering (OKVQA) requires an automatic system to answer natural language questions about pictures and images using external knowledge. We observe that many visual questions, which contain deictic referential phrases referring to entities in the image, can be rewritten as "non-grounded" questions and can be answered by existing text-based question answering systems. This allows for the reuse of existing text-based Open Domain Question Answering (QA) Systems for visual question answering. In this work, we propose a potentially data-efficient approach that reuses existing systems for (a) image analysis, (b) question rewriting, and (c) text-based question answering to answer such visual questions. Given an image and a question pertaining to that image (a visual question), we first extract the entities present in the image using pre-trained object and scene classifiers. Using these detected entities, the visual questions can be rewritten so as to be answerable by open domain QA systems. We explore two rewriting strategies: (1) an unsupervised method using BERT for masking and rewriting, and (2) a weakly supervised approach that combines adaptive rewriting and reinforcement learning techniques to use the implicit feedback from the QA system. We test our strategies on the publicly available OKVQA dataset and obtain a competitive performance with state-of-the-art models while using only 10% of the training data.

In a number of application domains, one observes a sequence of network data; for example, repeated measurements between users interactions in social media platforms, financial correlation networks over time, or across subjects, as in multi-subject studies of brain connectivity. One way to analyze such data is by stacking networks into a third-order array or tensor. We propose a principal components analysis (PCA) framework for sequence network data, based on a novel decomposition for semi-symmetric tensors. We derive efficient algorithms for computing our proposed "Coupled CP" decomposition and establish estimation consistency of our approach under an analogue of the spiked covariance model with rates the same as the matrix case up to a logarithmic term. Our framework inherits many of the strengths of classical PCA and is suitable for a wide range of unsupervised learning tasks, including identifying principal networks, isolating meaningful changepoints or outliers across observations, and for characterizing the "variability network" of the most varying edges. Finally, we demonstrate the effectiveness of our proposal on simulated data and on examples from political science and financial economics. The proof techniques used to establish our main consistency results are surprisingly straight-forward and may find use in a variety of other matrix and tensor decomposition problems.

Learning rate schedules are ubiquitously used to speed up and improve optimisation. Many different policies have been introduced on an empirical basis, and theoretical analyses have been developed for convex settings. However, in many realistic problems the loss-landscape is high-dimensional and non convex -- a case for which results are scarce. In this paper we present a first analytical study of the role of learning rate scheduling in this setting, focusing on Langevin optimization with a learning rate decaying as $\eta(t)=t^{-\beta}$. We begin by considering models where the loss is a Gaussian random function on the $N$-dimensional sphere ($N\rightarrow \infty$), featuring an extensive number of critical points. We find that to speed up optimization without getting stuck in saddles, one must choose a decay rate $\beta<1$, contrary to convex setups where $\beta=1$ is generally optimal. We then add to the problem a signal to be recovered. In this setting, the dynamics decompose into two phases: an \emph{exploration} phase where the dynamics navigates through rough parts of the landscape, followed by a \emph{convergence} phase where the signal is detected and the dynamics enter a convex basin. In this case, it is optimal to keep a large learning rate during the exploration phase to escape the non-convex region as quickly as possible, then use the convex criterion $\beta=1$ to converge rapidly to the solution. Finally, we demonstrate that our conclusions hold in a common regression task involving neural networks.

One of the most successful approaches to automated planning is the translation to propositional satisfiability (SAT). We employ incremental SAT solving to increase the capabilities of several modern encodings for SAT based planning. Experiments based on benchmarks from the 2014 International Planning Competition show that an incremental approach significantly outperforms non incremental solving. Although we are using sequential scheduling of makespans, we can outperform the state-of-the-art SAT based planning system Madagascar in the number of solved instances.

Classification of hand drawn sketches with respect to content quality is extremely challenging task, comparing to usual image classification methods. In brief, we need to train computational device to able to classify the images of the same object into different classes with respect their content quality. In this paper we tested several methods of image classification, using machine learning and computer vision algorithms, to classify Draw-a-Person test images sketched by primary school students in Nigeria, aged 4 to 11 years. We collected 1000 original sketches and manually classified them (using guidelines from existing literature) according to the ages (8 classes) before testing this dataset on a computational device. The highest accuracy achieved in this experiment was 62%.

Gupshup, the US-based conversational messaging services company, has strengthened its Middle East presence with the acquisition of Singapore-based Knowlarity Communications, a global leader in cloud communications. With voice technology reforming the customer experience in the Middle East and North Africa (MENA), this acquisition by Gupshup will ensure that with Artificial Intelligence (AI) voice technology, customers can effortlessly connect with businesses and get support or post-sales assistance. This technology will reduce response times of businesses to customers and eventually help businesses retain customers. With the addition of Knowlarity's products, Gupshup will now be able to support businesses in building seamless conversational experiences across both messaging and voice channels. "As business-to-consumer (B2C) engagement becomes conversational, Gupshup is busy enabling more ways for businesses to deliver rich experiences. With the addition of Knowlarity's products, our customers in the Middle East and across the world will now be able to build seamless conversational experiences across both messaging and voice channels. A large number of large businesses and SMEs across sectors in the Middle East are starting to integrate AI technologies into their business and we see a huge potential for our business in the Middle East market."