Humans can only interact with part of the surrounding environment due to biological restrictions. Therefore, we learn to reason the spatial relationships across a series of observations to piece together the surrounding environment. Inspired by such behavior and the fact that machines also have computational constraints, we propose \underline{CO}nditional \underline{CO}ordinate GAN (COCO-GAN) of which the generator generates images by parts based on their spatial coordinates as the condition. On the other hand, the discriminator learns to justify realism across multiple assembled patches by global coherence, local appearance, and edge-crossing continuity. Despite the full images are never generated during training, we show that COCO-GAN can produce \textbf{state-of-the-art-quality} full images during inference. We further demonstrate a variety of novel applications enabled by teaching the network to be aware of coordinates. First, we perform extrapolation to the learned coordinate manifold and generate off-the-boundary patches. Combining with the originally generated full image, COCO-GAN can produce images that are larger than training samples, which we called "beyond-boundary generation". We then showcase panorama generation within a cylindrical coordinate system that inherently preserves horizontally cyclic topology. On the computation side, COCO-GAN has a built-in divide-and-conquer paradigm that reduces memory requisition during training and inference, provides high-parallelism, and can generate parts of images on-demand.

Vikram Mahidhar reminds us all that AI is only as good as the humans supervising it and programming it. The biases and artefacts that come out of the processing are reflective of the biases programmed in at the beginning. A program trained to recognise totalled car bodies for insurance purposes, for example, will need close supervision of its decision-making outputs, for regulatory and consumer confidence and acceptance of the decision. There is a call and a growth in a new class of AI--one that is explainable, and that builds trust by providing evidence. Vikram also reminds us that a governance strategy is key to engendering trust in our organisation, processes and people.

In predictive process analytics, current and historical process data in event logs are used to predict future. E.g., to predict the next activity or how long a process will still require to complete. Recurrent neural networks (RNN) and its subclasses have been demonstrated to be well suited for creating prediction models. Thus far, event attributes have not been fully utilized in these models. The biggest challenge in exploiting them in prediction models is the potentially large amount of event attributes and attribute values. We present a novel clustering technique which allows for trade-offs between prediction accuracy and the time needed for model training and prediction. As an additional finding, we also found that this clustering method combined with having raw event attribute values provides even better prediction accuracy at the cost of additional time required for training and prediction. We also built a highly configurable test framework that can be used to efficiently evaluate different prediction approaches and parameterizations.

End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function approximation. Neural Episodic Control (NEC), which has been proposed in order to improve sample efficiency, is able to learn stably by estimating action values using a non-parametric method. In this paper, we propose an architecture that incorporates random projection into NEC to train with more stability. In addition, we verify the effectiveness of our architecture by Atari's five games. The main idea is to reduce the number of parameters that have to learn by replacing neural networks with random projection in order to reduce dimensions while keeping the learning end-to-end.

The standard Gibbs sampler of Mixed Multinomial Logit (MMNL) models involves sampling from conditional densities of utility parameters using Metropolis-Hastings (MH) algorithm due to unavailability of conjugate prior for logit kernel. To address this non-conjugacy concern, we propose the application of P\'olygamma data augmentation (PG-DA) technique for the MMNL estimation. The posterior estimates of the augmented and the default Gibbs sampler are similar for two-alternative scenario (binary choice), but we encounter empirical identification issues in the case of more alternatives ($J \geq 3$).

Is workplace surveillance about improving productivity or simply a way to control staff and weed out poor performers? Courtney Hagen Ford, 34, left her job working as a bank teller because she found the surveillance she was under was "dehumanising". Her employer logged her keystrokes and used software to monitor how many of the customers she helped went on to take out loans and fee-paying accounts. "The sales pressure was relentless," she recalls. She decided selling fast food would be better, but ironically, left the bank to do a doctorate in surveillance technology.

Recent research on Software-Defined Networking (SDN) strongly promotes the adoption of distributed controller architectures. To achieve high network performance, designing a scheduling function (SF) to properly dispatch requests from each switch to suitable controllers becomes critical. However, existing literature tends to design the SF targeted at specific network settings. In this paper, a reinforcement-learning-based (RL) approach is proposed with the aim to automatically learn a general, effective, and efficient SF. In particular, a new dispatching system is introduced in which the SF is represented as a neural network that determines the priority of each controller. Based on the priorities, a controller is selected using our proposed probability selection scheme to balance the trade-off between exploration and exploitation during learning. In order to train a general SF, we first formulate the scheduling function design problem as an RL problem. Then a new training approach is developed based on a state-of-the-art deep RL algorithm. Our simulation results show that our RL approach can rapidly design (or learn) SFs with optimal performance. Apart from that, the trained SF can generalize well and outperforms commonly used scheduling heuristics under various network settings.

The problem of explaining the behavior of deep neural networks has gained a lot of attention over the last years. While several attribution methods have been proposed, most come without strong theoretical foundations. This raises the question of whether the resulting attributions are reliable. On the other hand, the literature on cooperative game theory suggests Shapley values as a unique way of assigning relevance scores such that certain desirable properties are satisfied. Previous works on attribution methods also showed that explanations based on Shapley values better agree with the human intuition. Unfortunately, the exact evaluation of Shapley values is prohibitively expensive, exponential in the number of input features. In this work, by leveraging recent results on uncertainty propagation, we propose a novel, polynomial-time approximation of Shapley values in deep neural networks. We show that our method produces significantly better approximations of Shapley values than existing state-of-the-art attribution methods.

Alphabet's subsidiary Wing announced this week that it has officially launched a commercial drone delivery service "to a limited set of eligible homes in the suburbs of Crace, Palmerston and Franklin," which are just north of Canberra, in Australia. Wing's drones are able to drop a variety of small products, including coffee, food, and pharmacy items, shuttling them from local stores to customers' backyards within minutes. We've been skeptical about whether this kind of drone delivery makes sense for a long, long time, and while this is certainly a major milestone for Wing, I'm still not totally convinced that the use-cases that Wing is pushing here are going to be sustainable long term. I've still got a bunch of questions about these things. For example, does the drone have any kind of in-flight sense and avoid?

It is estimated that one in three rare and genetic diseases show up in these features, which could aid an earlier diagnosis. Researchers from Curtin University in Australia have developed a tool, as part of the Cliniface project, which scans the face, creating a 3D image. It then measures the distance between facial features and compares them with the average measurement for their ethnicity, sex and age according to their system. By way of example, they use Foetal Alcohol Spectrum Disorders (FASD), an umbrella term used to describe the range of effects caused by alcohol exposure in the uterus. Researchers have developed a too, called Cliniface, which scans the person's face and then creates a 3D image of it.