Constraint Programming (CP) is a well-established area in AI as a programming paradigm for modelling and solving discrete optimization problems, and it has been been successfully applied to tackle the on-line job dispatching problem in HPC systems including those running modern applications. The limitations of the available CP-based job dispatchers may hinder their practical use in today's systems that are becoming larger in size and more demanding in resource allocation. In an attempt to bring basic AI research closer to a deployed application, we present a new CP-based on-line job dispatcher for modern HPC systems and applications. Unlike its predecessors, our new dispatcher tackles the entire problem in CP and its model size is independent of the system size. Experimental results based on a simulation study show that with our approach dispatching performance increases significantly in a large system and in a system where allocation is nontrivial.

Botnet is one of the major threats to computer security. In previous botnet command and control (C&C) scenarios using online social networks (OSNs), methods for finding botmasters (e.g. ids, links, DGAs, etc.) are hardcoded into bots. Once a bot is reverse engineered, botmaster is exposed. Meanwhile, abnormal contents from explicit commands may expose botmaster and raise anomalies on OSNs. To overcome these deficiencies, we propose an AI-powered covert C&C channel. On leverage of neural networks, bots can find botmasters by avatars, which are converted into feature vectors. Commands are embedded into normal contents (e.g. tweets, comments, etc.) using text data augmentation and hash collision. Experiment on Twitter shows that the command-embedded contents can be generated efficiently, and bots can find botmaster and obtain commands accurately. By demonstrating how AI may help promote a covert communication on OSNs, this work provides a new perspective on botnet detection and confrontation.

However, the performance of AL heuristics depends on the structure of the underlying classifier model and the data. We propose an imitation learning scheme that imitates the selection of the best expert heuristic at each stage of the AL cycle in a batch-mode pool-based setting. With multiple AL heuristics as experts, the policy is able to reflect the choices of the best AL heuristics given the current state of the AL process. Our experiment on well-known datasets show that we both outperform state of the art imitation learners and heuristics. The high performance of deep learning on various tasks from computer vision (Voulodimos et al., 2018) to natural language processing (NLP) (Barrault et al., 2019) also comes with disadvantages. One of their main drawbacks is the large amount of labeled training data they require. Obtaining such data is expensive and time-consuming and often requires domain expertise (Löffler et al., 2020). Active Learning (AL) is an iterative process where during every iteration an oracle (e.g. a human) is asked to label the most informative unlabeled data sample(s). In pool-based AL all data samples are available (while most of them are unlabeled). In batch-mode pool-based AL, we select unlabeled data samples from the pool in acquisition batches greater than 1. Batch-mode AL decreases the number of AL iterations required and makes it easier for an oracle to label the data samples (Settles, 2009).

Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and parameterizes policies with either continuous Gaussian distributions or discrete Softmax distributions. These design choices are widely accepted, and motivated by empirical performance comparisons on MuJoCo and Atari benchmarks. We revisit these practices outside the regime of current benchmarks, and expose three failure modes of standard PPO. We explain why standard design choices are problematic in these cases, and show that alternative choices of surrogate objectives and policy parameterizations can prevent the failure modes. We hope that our work serves as a reminder that many algorithmic design choices in reinforcement learning are tied to specific simulation environments. We should not implicitly accept these choices as a standard part of a more general algorithm.

Learning in deep neural networks (DNNs) is implemented through minimizing a highly non-convex loss function, typically by a stochastic gradient descent (SGD) method. This learning process can effectively find good wide minima without being trapped in poor local ones. We present a novel account of how such effective deep learning emerges through the interactions of the SGD and the geometrical structure of the loss landscape. Rather than being a normal diffusion process (i.e. Brownian motion) as often assumed, we find that the SGD exhibits rich, complex dynamics when navigating through the loss landscape; initially, the SGD exhibits anomalous superdiffusion, which attenuates gradually and changes to subdiffusion at long times when the solution is reached. Such learning dynamics happen ubiquitously in different DNNs such as ResNet and VGG-like networks and are insensitive to batch size and learning rate. The anomalous superdiffusion process during the initial learning phase indicates that the motion of SGD along the loss landscape possesses intermittent, big jumps; this non-equilibrium property enables the SGD to escape from sharp local minima. By adapting the methods developed for studying energy landscapes in complex physical systems, we find that such superdiffusive learning dynamics are due to the interactions of the SGD and the fractal-like structure of the loss landscape. We further develop a simple model to demonstrate the mechanistic role of the fractal loss landscape in enabling the SGD to effectively find global minima. Our results thus reveal the effectiveness of deep learning from a novel perspective and have implications for designing efficient deep neural networks.

Bayesian inference engines have become established as an important paradigm for inference in arbitrarily large and complex graphical models. Software platforms such as Infer.NET (Minka et al., 2018) and Stan (Carpenter et al., 2017) are instances of such Bayesian inference engines. They deliver approximate Bayesian inference, with varying degrees of inferential accuracy, by calling upon contemporary approaches such as expectation propagation, Hamiltonian Monte Carlo and variational approximation. The purpose of this short article is to show that effective and scalable probability density function estimation, or density estimation for short, can be achieved using Bayesian inference engines. We provide easy access for users of the R statistical computing environment (R Core Team, 2018) via a package named densEstBayes (Wand, 2020).

In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons. Here, we depart from the classical perceptron and the elemental operations on quantum bits, i.e. qubits, so as to formulate the problem in terms of quantum perceptrons. We then make use of measurable operators to define the states of the network in a manner consistent with a Markov process. This yields a Dirac-Von Neumann formulation consistent with quantum mechanics. Moreover, the formulation presented here has the advantage of having a computational efficiency devoid of the number of layers in the network. This, paired with the natural efficiency of quantum computing, can imply a significant improvement in efficiency, particularly for deep networks. Finally, but not least, the developments here are quite general in nature since the approach presented here can also be used for quantum-inspired neural networks implemented on conventional computers.

One of the top 10 trends in data and analytics this year as leaders navigate the covid-19 world, according to Gartner, is "augmented data management." It's the growing use of tools with ML/AI to clean and prepare robust data for AI-based analytics. Companies are currently striving to go digital and derive insights from their data, but the roadblock is bad data, which leads to faulty decisions. "I was talking to a university dean the other day. It had 20,000 students in its database, but only 9,000 students had actually passed out of the university," says Deleep Murali, co-founder and CEO of Bengaluru-based Zscore. This kind of faulty data has a cascading effect because all kinds of decisions, including financial allocations, are based on it.

In addition to her roles as founder and CEO of fintech start-up Flamingo AI and as adjunct professor at the Australian Graduate School of Management, Dr Catriona Wallace is a campaigner for ethics in the artificial intelligence sector. She also helmed the second ever woman-led company to list on the ASX-listed company. Many people have concerns about our growing reliance on artificial intelligence. How do you feel about it? Artificial intelligence (AI) is the fastest-growing technology sector in the world, likely to replace 40 per cent of jobs in the next five years, especially in industries such as tourism, media, telecommunications and banking.

Image registration is a widely-used technique in analysing large scale datasets that are captured through various imaging modalities and techniques in biomedical imaging such as MRI, X-Rays, etc. These datasets are typically collected from various sites and under different imaging protocols using a variety of scanners. Such heterogeneity in the data collection process causes inhomogeneity or variation in intensity (brightness) and noise distribution. These variations play a detrimental role in the performance of image registration, segmentation and detection algorithms. Classical image registration methods are computationally expensive but are able to handle these artifacts relatively better. However, deep learning-based techniques are shown to be computationally efficient for automated brain registration but are sensitive to the intensity variations. In this study, we investigate the effect of variation in intensity distribution among input image pairs for deep learning-based image registration methods. We find a performance degradation of these models when brain image pairs with different intensity distribution are presented even with similar structures. To overcome this limitation, we incorporate a structural similarity-based loss function in a deep neural network and test its performance on the validation split separated before training as well as on a completely unseen new dataset. We report that the deep learning models trained with structure similarity-based loss seems to perform better for both datasets. This investigation highlights a possible performance limiting factor in deep learning-based registration models and suggests a potential solution to incorporate the intensity distribution variation in the input image pairs. Our code and models are available at https://github.com/hassaanmahmood/DeepIntense.